© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7418
    Prev
    Next
    INDEX
    Explanations

    medical/pharmacology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ichen
    -0.28
    аÑĢÑĤ
    -0.26
    alist
    -0.26
    asc
    -0.25
    #endif
    -0.25
    èĤ©èĨĢ
    -0.25
    amar
    -0.25
    认åIJĮ
    -0.24
    [/
    -0.24
    fen
    -0.24
    POSITIVE LOGITS
    mania
    0.29
    -style
    0.26
    nore
    0.25
    èĩªçĶ±è´¸æĺĵ
    0.25
    constitution
    0.23
    apyrus
    0.23
    æĸ¹éĿ¢
    0.23
    å¹ķåIJİ
    0.23
     lottery
    0.23
     Bomb
    0.23
    Activations Density 0.052%

    No Known Activations