© 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. 35-TRANSCODER-HP
    7. 39058
    Prev
    Next
    INDEX
    Explanations

    anatomical/medical terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uncont
    -0.25
    å¨Ħ
    -0.24
    çŃī缸åħ³
    -0.24
     contenders
    -0.24
    é²į
    -0.23
    .serializer
    -0.23
    æĹ¥åĩĮæĻ¨
    -0.23
     emptied
    -0.23
     tipped
    -0.23
     paused
    -0.23
    POSITIVE LOGITS
    erc
    0.31
    ultip
    0.31
    vale
    0.28
    vx
    0.28
    suit
    0.27
    wards
    0.27
    vak
    0.27
    verse
    0.27
    sv
    0.26
    v
    0.26
    Activations Density 0.051%

    No Known Activations