© 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. 31-TRANSCODER-HP
    7. 17772
    Prev
    Next
    INDEX
    Explanations

    medicine dosages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ç»Ļ
    -0.41
    ç»Ļ人
    -0.37
    åıĸ
    -0.34
    Giving
    -0.31
     giving
    -0.30
    ivor
    -0.29
    give
    -0.28
    給
    -0.28
     Giving
    -0.27
    oders
    -0.26
    POSITIVE LOGITS
     gu
    0.29
    gu
    0.27
    èĤļ
    0.27
    entities
    0.26
    enz
    0.25
    Gu
    0.25
    duc
    0.25
    饿
    0.25
    quia
    0.25
    שת
    0.25
    Activations Density 0.076%

    No Known Activations