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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RESID-POST-AA
    11. 41018
    Prev
    Next
    INDEX
    Explanations

    relationship advice

    np_max-act · gemini-2.0-flash

    sentences or phrases addressing the reader directly (second-person “you/your”)—especially advice or guidance about relationships.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     effortlessly
    -0.07
     <$
    -0.07
    .SYSTEM
    -0.07
    startup
    -0.06
     FAMILY
    -0.06
    언
    -0.06
     Utilities
    -0.06
    ❌
    -0.06
     Eğitim
    -0.06
    吃饭
    -0.06
    POSITIVE LOGITS
    开设
    0.07
     apoptosis
    0.07
     syn
    0.07
     comm
    0.07
    ihanna
    0.06
    甚至连
    0.06
     Liebe
    0.06
    croft
    0.06
    ॰
    0.06
     cosplay
    0.06
    Activations Density 0.531%

    No Known Activations