© 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. 32-TRANSCODER-HP
    7. 42786
    Prev
    Next
    INDEX
    Explanations

    military/government abbreviations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ATA
    -0.32
    enda
    -0.29
    code
    -0.27
     well
    -0.27
    ftar
    -0.26
    edly
    -0.26
    .Code
    -0.26
    well
    -0.26
    Code
    -0.25
    õ
    -0.25
    POSITIVE LOGITS
     Molecular
    0.29
    å¸ĤéĿ¢ä¸Ĭ
    0.28
     dy
    0.28
     finished
    0.27
    ax
    0.27
    åĪĨåŃIJ
    0.27
    MIC
    0.26
    axy
    0.26
     molecular
    0.26
    (ax
    0.26
    Activations Density 0.003%

    No Known Activations