© 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. 12-TRANSCODER-HP
    7. 22018
    Prev
    Next
    INDEX
    Explanations

    Disease

    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
    Negative Logits
    íĸī
    -0.26
    rag
    -0.26
    æµ´
    -0.26
    è¾½
    -0.25
    acting
    -0.25
    plate
    -0.25
    çłĶ究表æĺİ
    -0.24
     Plate
    -0.24
    rule
    -0.24
    AL
    -0.24
    POSITIVE LOGITS
    ipi
    0.29
    InitialState
    0.27
     gá»ijc
    0.26
    éĴ»
    0.26
     zelf
    0.26
     qualification
    0.25
    dbe
    0.24
    IBUT
    0.23
    [path
    0.23
     {}.
    0.23
    Activations Density 0.002%

    No Known Activations