© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 23496
    Prev
    Next
    INDEX
    Explanations

    Mixed code and text

    np_max-act · gemini-2.0-flash

    markers indicating the assistant’s turn or the start of an assistant message in chat-formatted transcripts.

    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
    ガ
    -0.06
    ㊤
    -0.06
    Fel
    -0.06
     fiber
    -0.06
    رهاب
    -0.06
     specific
    -0.06
    웝
    -0.06
     Тур
    -0.06
    ,N
    -0.06
    촘
    -0.06
    POSITIVE LOGITS
     sieht
    0.07
    acus
    0.07
    Africa
    0.07
    .ctrl
    0.07
     יהיה
    0.07
     outbound
    0.07
    杌
    0.07
    卡车
    0.07
    shelf
    0.07
     Methodist
    0.07
    Activations Density 0.019%

    No Known Activations