© 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 EvalsExportsinterp-engineNEWAPI 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. 55009
    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
    有钱
    -0.07
     refused
    -0.06
    _rpc
    -0.06
     Cho
    -0.06
    رحل
    -0.06
    使える
    -0.06
    とって
    -0.06
     benefiting
    -0.06
    🏷
    -0.06
     incredibly
    -0.06
    POSITIVE LOGITS
    Disappear
    0.07
     §§
    0.07
    нал
    0.07
    arrière
    0.07
    square
    0.07
     Sty
    0.07
     су
    0.07
     severity
    0.06
    .userService
    0.06
     **)&
    0.06
    Activations Density 0.010%

    No Known Activations