© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29318
    Prev
    Next
    INDEX
    Explanations

    scantily clad/striptease

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     управ
    -0.08
    enville
    -0.07
    Turn
    -0.07
    .changed
    -0.07
     koń
    -0.07
     resett
    -0.07
     القاد
    -0.07
     Modes
    -0.07
     Seminar
    -0.07
     wanna
    -0.07
    POSITIVE LOGITS
    ,body
    0.07
     ssize
    0.07
    istas
    0.07
    _REPLY
    0.07
    -describedby
    0.07
     creativity
    0.07
     Dutch
    0.07
     newspaper
    0.06
    革命
    0.06
     Les
    0.06
    Activations Density 0.116%

    No Known Activations