© 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. 87003
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    /support
    -0.31
    itta
    -0.28
    çĻ»åľº
    -0.26
     LATIN
    -0.26
    (\'
    -0.25
    çĤ¯
    -0.25
    讵
    -0.24
    /format
    -0.24
    utive
    -0.24
     Yelp
    -0.24
    POSITIVE LOGITS
    e
    0.28
    è¿ĺæľī
    0.26
    ın
    0.26
    a
    0.25
    lin
    0.24
    cri
    0.24
    Consider
    0.23
     lẫn
    0.23
    äºĴ
    0.23
    è¿ĺæľīå¾Īå¤ļ
    0.23
    Activations Density 0.002%

    No Known Activations