© 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. 129103
    Prev
    Next
    INDEX
    Explanations

    Code, URLs, or citations

    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
    å²ģæŶ
    -0.30
    umo
    -0.28
    ĽĦ
    -0.27
    oria
    -0.25
    OND
    -0.24
    ';č↵
    -0.24
    GINE
    -0.24
     cons
    -0.23
    èĭ¥æľī
    -0.23
    aby
    -0.23
    POSITIVE LOGITS
    imento
    0.25
    ptive
    0.25
    _Dep
    0.24
     Ãĸn
    0.24
    åĹĵåŃIJ
    0.24
     $_[
    0.23
    çªģåĩºéĹ®é¢ĺ
    0.23
    inally
    0.23
     Param
    0.22
    ç¦ģå¿Į
    0.22
    Activations Density 0.007%

    No Known Activations