© 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. 44177
    Prev
    Next
    INDEX
    Explanations

    software licenses

    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
    inois
    -0.35
     up
    -0.30
    ins
    -0.29
    èµ·æĿ¥
    -0.28
    inz
    -0.27
    忽
    -0.27
    ination
    -0.27
    in
    -0.27
    innen
    -0.26
     pageNo
    -0.26
    POSITIVE LOGITS
    rap
    0.32
    ting
    0.31
    yp
    0.31
    tons
    0.28
     sph
    0.28
    woods
    0.27
    rape
    0.27
     Storage
    0.27
     lith
    0.26
     Oct
    0.26
    Activations Density 0.001%

    No Known Activations