© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 23660
    Prev
    Next
    INDEX
    Explanations

    HTML-like formatting

    np_max-act · gemini-2.0-flash

    brief conversational greetings and small‑talk openings in chat dialogues.

    oai_token-act-pair · gpt-5Triggered by @vetterc0

    conversational greetings and opening salutations in chat-style dialogue.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    grep
    -0.07
    ait
    -0.07
     Utt
    -0.07
    (typeof
    -0.06
     baptized
    -0.06
    ᥒ
    -0.06
     transmitting
    -0.06
    Akt
    -0.06
    adata
    -0.06
     Stadt
    -0.06
    POSITIVE LOGITS
     Operations
    0.08
    הצעה
    0.08
     apologies
    0.08
    נגר
    0.07
     menstrual
    0.07
    巫
    0.07
    �
    0.07
    主力
    0.07
     commem
    0.07
     prostate
    0.07
    Activations Density 0.040%

    No Known Activations