© 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. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 88062
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pand
    -0.27
    åı®
    -0.26
    riage
    -0.26
    Lik
    -0.25
    hest
    -0.25
    gc
    -0.24
     posed
    -0.24
    人éĹ´
    -0.23
    INATION
    -0.23
     Pel
    -0.23
    POSITIVE LOGITS
    çļĦèĦ¸
    0.29
    ä¸įåIJĪéĢĤ
    0.28
    è¿Ļ件
    0.27
    sein
    0.27
     SUBSTITUTE
    0.27
    /Area
    0.27
    atif
    0.26
    enido
    0.26
     Drag
    0.25
     côté
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.