© 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. 41004
    Prev
    Next
    INDEX
    Explanations

    timeframes or use cases

    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
    hani
    -0.33
    manship
    -0.31
    _Des
    -0.29
    _design
    -0.28
    çļĦ设计
    -0.28
     Design
    -0.28
     Modelo
    -0.28
    hab
    -0.28
    夫
    -0.27
    设计
    -0.26
    POSITIVE LOGITS
     flipping
    0.29
    utta
    0.26
     cycling
    0.25
    enk
    0.25
    tering
    0.24
    uttle
    0.24
    olen
    0.24
     nonzero
    0.24
     towing
    0.24
     precise
    0.24
    Activations Density 0.004%

    No Known Activations