© 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. 41036
    Prev
    Next
    INDEX
    Explanations

    in

    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
    BUS
    -0.26
    满
    -0.26
    åħĪè¿Ľ
    -0.26
    滿
    -0.25
    Ỽ
    -0.25
    éªĮ
    -0.24
    .mozilla
    -0.24
    åĥĸ
    -0.24
    áz
    -0.24
     Vent
    -0.24
    POSITIVE LOGITS
    integral
    0.31
    å¤ĸåĽ´
    0.27
     integral
    0.27
     ad
    0.27
     inner
    0.26
     outer
    0.26
    ä¾Ŀ
    0.26
    Sher
    0.26
    ç¡®åĪĩ
    0.25
    Merit
    0.25
    Activations Density 0.001%

    No Known Activations