© 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. 112830
    Prev
    Next
    INDEX
    Explanations

    code symbols

    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
    Not in Any Lists

    No Comments

    Negative Logits
    [h
    -0.27
    __).
    -0.27
    ania
    -0.27
     cleanly
    -0.26
     timely
    -0.25
    èĸĦ
    -0.24
    æīĵåį¡
    -0.24
    ãĥĨãĤ£ãĥĸ
    -0.24
    -del
    -0.24
    ÂŃs
    -0.23
    POSITIVE LOGITS
     Compound
    0.27
    ä¼łè¯´
    0.25
    ses
    0.25
    ä»ĸ们æĺ¯
    0.24
    tls
    0.24
    è·Ĺ
    0.24
    çľĭä¸įåĩº
    0.24
     compound
    0.24
    trinsic
    0.23
     tls
    0.23
    Activations Density 0.229%

    No Known Activations