© 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. 12-TRANSCODER-HP
    7. 23261
    Prev
    Next
    INDEX
    Explanations

    predicting patient outcomes/drug response

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľ½
    -0.27
    è¡ĢèĦĤ
    -0.27
    æĽ¿æį¢
    -0.25
     poles
    -0.25
    benchmark
    -0.25
     FOUND
    -0.24
    çį
    -0.24
     zeroes
    -0.24
    éĽĢ
    -0.24
    ç©·
    -0.24
    POSITIVE LOGITS
    acks
    0.27
    æ´Ĵ
    0.27
     focused
    0.25
    aku
    0.25
     suck
    0.25
     stake
    0.24
    æĦı大
    0.24
    äºĨä¸Ģåı£
    0.24
    éĴŀ
    0.24
    ishi
    0.24
    Activations Density 0.001%

    No Known Activations