© 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. 98068
    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
    åı°ä¸Ĭ
    -0.27
     taller
    -0.26
    IOUS
    -0.25
     richness
    -0.25
    ITH
    -0.25
    eland
    -0.23
     sisters
    -0.23
     max
    -0.23
     min
    -0.23
    æĹĮ
    -0.23
    POSITIVE LOGITS
    µľ
    0.27
    åħ±éĿĴ
    0.26
    妨
    0.25
    (SS
    0.25
    PURE
    0.25
     Nack
    0.25
    ä¸įè¿ĩæĺ¯
    0.25
    æĹ¥æĬ¥éģĵ
    0.24
     Comb
    0.24
    _fold
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.