© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RESID-POST-AA
    6. 1505
    Prev
    Next
    INDEX
    Explanations

    ertext

    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
    Jesteś
    -0.07
    .onChange
    -0.07
    حسب
    -0.07
     sends
    -0.07
    层出不
    -0.07
    目的
    -0.06
     sdf
    -0.06
    )])↵↵
    -0.06
    ŭ
    -0.06
    净
    -0.06
    POSITIVE LOGITS
    (age
    0.07
    elope
    0.07
    specs
    0.07
    商业
    0.06
     Ajax
    0.06
     Papers
    0.06
    ownership
    0.06
    srv
    0.06
     fuels
    0.06
    getParam
    0.06
    Activations Density 0.001%

    No Known Activations