© 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. 129473
    Prev
    Next
    INDEX
    Explanations

    medical procedures and drugs

    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
    æīģ
    -0.31
    åIJ²
    -0.28
    éĴĿ
    -0.28
    Compilation
    -0.26
    å«Į
    -0.26
    æ±ł
    -0.26
     Clerk
    -0.26
     defaultMessage
    -0.25
    èĩªè´Ł
    -0.25
    ç®Ĺ
    -0.24
    POSITIVE LOGITS
    verter
    0.31
    epad
    0.30
    仪
    0.29
    icide
    0.27
    изаÑĤоÑĢ
    0.26
     Viking
    0.26
    åľ¨æ·±åľ³
    0.25
    ona
    0.25
    Impossible
    0.25
    ix
    0.25
    Activations Density 0.136%

    No Known Activations