© 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. 88810
    Prev
    Next
    INDEX
    Explanations

    Abbreviations

    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
    ä¸Ģè§Ī
    -0.27
    çŁ¥éģĵèĩªå·±
    -0.27
    æ¯Ķäºļ
    -0.27
    ä¸ŃåİŁ
    -0.26
    FunctionFlags
    -0.26
     Bik
    -0.25
    bial
    -0.25
    åħ´ä¸ļ
    -0.24
    mA
    -0.24
    ä¸ĩåħĥ以ä¸Ĭ
    -0.24
    POSITIVE LOGITS
    主å¸Ń
    0.32
     use
    0.29
     also
    0.27
    éĻĦ
    0.27
    åħ±
    0.26
     requests
    0.26
    Use
    0.25
     uses
    0.24
    str
    0.24
    ulk
    0.24
    Activations Density 0.011%

    No Known Activations