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. 24601
    Prev
    Next
    INDEX
    Explanations

    Forum URLs

    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
    .Success
    -0.08
    蝻
    -0.08
    🅐
    -0.07
     UIBar
    -0.07
    สะดวก
    -0.07
    兴趣
    -0.07
    ’ex
    -0.07
     treści
    -0.07
    PLICIT
    -0.07
    scroll
    -0.07
    POSITIVE LOGITS
    🧙
    0.07
     EVENT
    0.06
    萧
    0.06
    中方
    0.06
    HH
    0.06
    耐用
    0.06
    不排除
    0.06
     Loose
    0.06
     trú
    0.06
     Funeral
    0.06
    Activations Density 0.000%

    No Known Activations