Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 36426
    Prev
    Next
    INDEX
    Explanations

    4

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _iter
    -0.07
    副校长
    -0.07
     Israelis
    -0.07
     живот
    -0.07
     Phú
    -0.07
    XYZ
    -0.07
    }/{
    -0.07
    逝世
    -0.06
    幞
    -0.06
    王
    -0.06
    POSITIVE LOGITS
    coupon
    0.07
     Equity
    0.07
    []>↵
    0.07
    이며
    0.07
    exec
    0.07
    /**↵
    0.07
    meg
    0.07
    {})↵
    0.06
    feedback
    0.06
    £
    0.06
    Activations Density 0.001%

    No Known Activations