© 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. 33-TRANSCODER-HP
    7. 52800
    Prev
    Next
    INDEX
    Explanations

    bodily fluids/medical procedures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tender
    -0.28
     sap
    -0.28
    æ´ŀ
    -0.28
    cone
    -0.26
     coup
    -0.25
     arg
    -0.24
     liquids
    -0.24
    液
    -0.24
     corps
    -0.23
     CST
    -0.23
    POSITIVE LOGITS
    æīĪ
    0.29
    uestion
    0.27
    _tolerance
    0.27
    ettle
    0.26
    berger
    0.26
    åĩºä¾Ĩ
    0.26
     disposition
    0.25
    éģĵ
    0.25
    olle
    0.25
    inality
    0.25
    Activations Density 0.018%

    No Known Activations