© 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. 15-RESID-POST-AA
    6. 11505
    Prev
    Next
    INDEX
    Explanations

    use

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    尊重
    -0.07
     الم
    -0.07
    CTIONS
    -0.07
    (
    -0.07
    /basic
    -0.07
    ITHUB
    -0.07
    赇
    -0.07
    看电视
    -0.06
    <Mesh
    -0.06
    /umd
    -0.06
    POSITIVE LOGITS
    硕
    0.07
    🖱
    0.07
    شو
    0.07
    arters
    0.07
    .pa
    0.07
    bak
    0.07
    _DRV
    0.07
     łatwo
    0.06
    写的
    0.06
     đo
    0.06
    Activations Density 0.030%

    No Known Activations