© 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. 97292
    Prev
    Next
    INDEX
    Explanations

    years and decades

    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
     courtesy
    -0.26
    /
    -0.26
    edom
    -0.25
    uch
    -0.25
     extracted
    -0.25
    ponder
    -0.25
    é¦į
    -0.24
    éĢŀ
    -0.24
    (or
    -0.24
    å»·
    -0.24
    POSITIVE LOGITS
    æ¡ĮéĿ¢
    0.29
    UDA
    0.27
    æĸĩåĮĸåĴĮ
    0.27
    æį¢äºĨ
    0.27
    spir
    0.26
    -Series
    0.26
    erial
    0.24
     Dü
    0.24
     millennium
    0.24
    OPSIS
    0.24
    Activations Density 0.006%

    No Known Activations