© 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. 40619
    Prev
    Next
    INDEX
    Explanations

    tract

    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
    倒
    -0.08
    posing
    -0.07
    (bbox
    -0.07
    Bet
    -0.07
     cấp
    -0.07
    奇纳
    -0.06
     iceberg
    -0.06
    _pow
    -0.06
    ₡
    -0.06
    娃
    -0.06
    POSITIVE LOGITS
    糍
    0.07
    特长
    0.07
    ﺨ
    0.07
     knull
    0.07
    主要从事
    0.07
    ᴻ
    0.07
    𝒃
    0.07
    新冠疫情
    0.07
     Word
    0.07
     Cartoon
    0.07
    Activations Density 0.005%

    No Known Activations