© 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. 97226
    Prev
    Next
    INDEX
    Explanations

    Legal/Academic documents

    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
    ç¼ħ
    -0.26
    ropriate
    -0.25
    olatile
    -0.25
    alties
    -0.25
     appropriate
    -0.23
    igated
    -0.23
    appropriate
    -0.23
    .esp
    -0.23
     exhaustive
    -0.23
    omore
    -0.23
    POSITIVE LOGITS
    è¯į
    0.25
    åľ¨åIJĮä¸Ģ
    0.24
    Ele
    0.24
     treÅĽci
    0.24
    è¶ĭ
    0.24
    æİ¥
    0.23
    ä¸Ĭæľī
    0.23
    LK
    0.22
    åľ¨åºĬä¸Ĭ
    0.22
     mö
    0.22
    Activations Density 0.009%

    No Known Activations