© 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. 41898
    Prev
    Next
    INDEX
    Explanations

    open positions

    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
     Greeks
    -0.29
    åºĵéĩĮ
    -0.29
    ä¸ŃåĽ½äºº
    -0.28
     Australians
    -0.27
     Italians
    -0.25
    "]}↵
    -0.25
    [url
    -0.24
     Karn
    -0.24
     internally
    -0.24
     Christians
    -0.24
    POSITIVE LOGITS
     positions
    0.39
     roles
    0.36
     seats
    0.29
     places
    0.29
     bil
    0.29
     charges
    0.29
     stops
    0.29
     addresses
    0.28
     ranks
    0.28
     occupations
    0.27
    Activations Density 0.004%

    No Known Activations