© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 35583
    Prev
    Next
    INDEX
    Explanations

    Kenny

    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
     sustaining
    -0.07
    ission
    -0.07
    动机
    -0.06
     okhttp
    -0.06
     Bild
    -0.06
    ออกจาก
    -0.06
    參加
    -0.06
    |↵
    -0.06
    Ỡ
    -0.06
    }(
    -0.06
    POSITIVE LOGITS
    drawer
    0.09
     BRAND
    0.07
    readOnly
    0.07
    Ⱄ
    0.07
     تعال
    0.07
    理发
    0.07
    silent
    0.07
    แช
    0.07
    ephir
    0.07
    .TRUE
    0.07
    Activations Density 0.003%

    No Known Activations