© 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. 7-RESID-POST-AA
    11. 8457
    Prev
    Next
    INDEX
    Explanations

    в

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Discover
    -0.07
     closest
    -0.07
    ƣ
    -0.07
    겡
    -0.07
    .Dense
    -0.06
     cells
    -0.06
    Fitness
    -0.06
    冷链物流
    -0.06
    鲋
    -0.06
    镄
    -0.06
    POSITIVE LOGITS
     sposób
    0.07
    .setHorizontalAlignment
    0.07
    亳
    0.07
    StyleSheet
    0.07
     IllegalArgumentException
    0.07
    NSNumber
    0.07
    不公平
    0.07
     doesnt
    0.07
    .StylePriority
    0.07
     __________________________________
    0.07
    Activations Density 0.001%

    No Known Activations