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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 69282
    Prev
    Next
    INDEX
    Explanations

    up

    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
     <$>
    -0.08
    센터
    -0.07
    .num
    -0.07
    颋
    -0.07
    색
    -0.07
    /XML
    -0.07
    战略布局
    -0.06
    涵
    -0.06
     sque
    -0.06
    馧
    -0.06
    POSITIVE LOGITS
    不良
    0.08
    (ra
    0.08
     Italian
    0.08
    良
    0.08
     Ig
    0.08
    铁
    0.07
    酒精
    0.07
    state
    0.07
    -prom
    0.07
    Ingredients
    0.07
    Activations Density 0.001%

    No Known Activations