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. 7097
    Prev
    Next
    INDEX
    Explanations

    version

    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
    증
    -0.07
    呈现
    -0.07
     rsa
    -0.07
    向往
    -0.06
    怠
    -0.06
    _web
    -0.06
    报纸
    -0.06
    村党支部
    -0.06
    බ
    -0.06
     והיא
    -0.06
    POSITIVE LOGITS
     mic
    0.07
     Variant
    0.07
    特产
    0.07
     Locations
    0.07
     Officers
    0.07
     receivers
    0.06
    oho
    0.06
     rib
    0.06
    nim
    0.06
     departed
    0.06
    Activations Density 0.000%

    No Known Activations