© 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. 88900
    Prev
    Next
    INDEX
    Explanations

    Dates and numerical references

    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
    arium
    -0.25
     similarly
    -0.25
    utter
    -0.24
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.24
    èµ°å¾Ĺ
    -0.24
    ovan
    -0.24
     mã
    -0.24
    åIJĮæł·
    -0.23
    ç»Ĭ
    -0.23
     $?
    -0.23
    POSITIVE LOGITS
     HAR
    0.32
     negativity
    0.27
    PLY
    0.26
    _ud
    0.26
    breaking
    0.26
    fst
    0.25
     motivating
    0.24
     intuit
    0.24
    FetchRequest
    0.24
    cks
    0.24
    Activations Density 0.014%

    No Known Activations