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

    Neuronpedia

    Jacobian LensNEW
    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. 15-RESID-POST-AA
    11. 78279
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    的可能性
    -0.07
    孩子
    -0.07
    equals
    -0.07
    的朋友
    -0.06
    ני
    -0.06
    .utils
    -0.06
    addGroup
    -0.06
    difference
    -0.06
    boolean
    -0.06
    큐
    -0.06
    POSITIVE LOGITS
    _SK
    0.07
    清澈
    0.07
    🏗
    0.07
    馊
    0.07
    AspNet
    0.07
    �
    0.07
    blood
    0.07
    _logs
    0.06
    (connectionString
    0.06
     Bakan
    0.06
    Activations Density 0.336%

    No Known Activations