© 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. 11-RESID-POST-AA
    6. 87658
    Prev
    Next
    INDEX
    Explanations

    toxins and pollutants

    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
     Hill
    -0.07
    Google
    -0.07
     store
    -0.07
    ียน
    -0.07
    _record
    -0.07
     University
    -0.07
    .source
    -0.07
    IC
    -0.07
    metric
    -0.07
     interface
    -0.07
    POSITIVE LOGITS
     состоит
    0.08
    👴
    0.07
    鲪
    0.07
    萄
    0.07
    楂
    0.07
    wis
    0.07
    圾
    0.07
    璈
    0.07
     Penalty
    0.07
    .sendKeys
    0.07
    Activations Density 0.070%

    No Known Activations