© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97245
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
    è¡·å¿ĥ
    -0.28
    lö
    -0.26
     saÄŁ
    -0.26
    è¡·
    -0.25
    emain
    -0.24
    è¯ļ
    -0.24
     vẻ
    -0.24
    ç¨į
    -0.24
    çļĦæĦıä¹ī
    -0.24
    çļĦé£İéĻ©
    -0.24
    POSITIVE LOGITS
    æĮĤ
    0.27
     brushes
    0.25
    atar
    0.25
    åı«åģļ
    0.25
     Experimental
    0.25
    AND
    0.24
    itere
    0.24
     preparation
    0.24
     called
    0.23
    ist
    0.23
    Activations Density 0.007%

    No Known Activations