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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 41519
    Prev
    Next
    INDEX
    Explanations

    IPA

    np_max-act · gemini-2.0-flash
    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
     reminis
    -0.07
    🧸
    -0.07
    prediction
    -0.07
     대해서
    -0.07
    我又
    -0.07
    ."',
    -0.07
    DK
    -0.06
    待遇
    -0.06
    nombre
    -0.06
     Kashmir
    -0.06
    POSITIVE LOGITS
    큇
    0.07
    酞
    0.07
    que
    0.07
     barrel
    0.06
    于此
    0.06
    unce
    0.06
     operate
    0.06
    亿元以上
    0.06
    쉴
    0.06
    erto
    0.06
    Activations Density 0.001%

    No Known Activations