© 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. 7-RESID-POST-AA
    6. 102476
    Prev
    Next
    INDEX
    Explanations

    Non-English, typos, conversational

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ドラ
    -0.08
    Key
    -0.07
    สรร
    -0.07
    숱
    -0.07
    就好
    -0.07
    attach
    -0.07
    に向
    -0.07
    師
    -0.07
     sorts
    -0.07
    .completed
    -0.06
    POSITIVE LOGITS
     ((
    0.07
     Continued
    0.07
    blems
    0.07
     않고
    0.07
    否则
    0.07
    (holder
    0.06
    .delta
    0.06
    '</
    0.06
    퓐
    0.06
    民眾
    0.06
    Activations Density 0.306%

    No Known Activations