© 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. 41650
    Prev
    Next
    INDEX
    Explanations

    code and dates

    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
     muchas
    -0.07
    Bas
    -0.07
    罨
    -0.07
    占用
    -0.07
     Tags
    -0.06
    (Vec
    -0.06
    );?>↵
    -0.06
    桂花
    -0.06
    .Abstractions
    -0.06
     gfx
    -0.06
    POSITIVE LOGITS
    StyleSheet
    0.07
    KT
    0.07
    ScreenState
    0.06
     الدكت
    0.06
    @Component
    0.06
    bridge
    0.06
     proclaim
    0.06
    이라
    0.06
    信息技术
    0.06
    دول
    0.06
    Activations Density 0.012%

    No Known Activations