© 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. 32-TRANSCODER-HP
    7. 44207
    Prev
    Next
    INDEX
    Explanations

    Medical diagnostics and imaging

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çIJħ
    -0.28
    linky
    -0.26
    ket
    -0.26
    terr
    -0.26
    å¤ĸ壳
    -0.26
    anos
    -0.26
    Lens
    -0.25
    aldo
    -0.25
    çħ¦
    -0.25
    alyze
    -0.24
    POSITIVE LOGITS
    çŃĸçķ¥
    0.33
     trials
    0.29
     modal
    0.28
     rad
    0.28
    orus
    0.27
     anc
    0.27
    è¾IJ
    0.27
    FML
    0.27
     ordered
    0.27
     ordering
    0.26
    Activations Density 0.034%

    No Known Activations