© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 130099
    Prev
    Next
    INDEX
    Explanations

    Medical terms

    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
    é»İ
    -0.29
    rå
    -0.28
    heimer
    -0.26
    keh
    -0.26
    prech
    -0.24
    ardo
    -0.24
    ningen
    -0.24
    åħ¨ä¸ĸçķĮ
    -0.24
    xCC
    -0.23
    深深
    -0.23
    POSITIVE LOGITS
    vere
    0.28
     Caucus
    0.26
    `,
    0.26
     -,
    0.25
    路桥
    0.25
    ë²
    0.24
    ert
    0.24
    à¹Ĥà¸ķ
    0.24
    è¾¾æłĩ
    0.24
    åħŃ大
    0.23
    Activations Density 0.078%

    No Known Activations