© 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. 50925
    Prev
    Next
    INDEX
    Explanations

    medical condition

    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
    十年
    -0.07
    وض
    -0.07
    向け
    -0.07
    ^[
    -0.07
    .matcher
    -0.06
     consult
    -0.06
     Winners
    -0.06
    _WP
    -0.06
    Nb
    -0.06
    👳
    -0.06
    POSITIVE LOGITS
    实际上是
    0.09
    ,
    0.07
     nämlich
    0.07
    écran
    0.07
    volução
    0.07
    طال
    0.07
    因为他
    0.07
    Cancelar
    0.07
    하도록
    0.06
    每个人
    0.06
    Activations Density 0.004%

    No Known Activations