© 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. 87272
    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
    豨
    -0.28
    é½IJ
    -0.28
    edException
    -0.26
     Ãĸn
    -0.26
    aÄŁ
    -0.26
    éĩįéĩį
    -0.25
    .ro
    -0.25
    ("↵
    -0.25
    çİĭæľĿ
    -0.24
    åħ¥æīĭ
    -0.24
    POSITIVE LOGITS
    æĽ´å¥½çļĦ
    0.29
    chy
    0.28
    byss
    0.28
     Gow
    0.26
    à¸ķà¸Ļ
    0.26
    “She
    0.25
    ÑĥÑħ
    0.25
     Gerr
    0.25
    æ¶Īè´¹èĢħçļĦ
    0.25
    &amp
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.