© 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. 88228
    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
    æĸ¹å¼ıè¿Ľè¡Į
    -0.28
    çĤ¹å¤ļ
    -0.26
    æŃ¥æŃ¥
    -0.26
    å¦Ĥæŀľè¯´
    -0.25
    deb
    -0.25
    带æĿ¥äºĨ
    -0.25
    à¸ŀ
    -0.25
    ç¢ĩ
    -0.24
     Forget
    -0.24
    arian
    -0.24
    POSITIVE LOGITS
     Suns
    0.32
    åľ¨èģĮ
    0.25
    edly
    0.25
     perc
    0.25
    ernals
    0.25
    [${
    0.24
    pez
    0.24
    /GPL
    0.24
     !↵
    0.23
     primaries
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.