© 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. 41261
    Prev
    Next
    INDEX
    Explanations

    Locations or brand names

    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
    hel
    -0.30
     hel
    -0.28
    gend
    -0.27
     hus
    -0.26
    åѵåĮĸåĻ¨
    -0.25
    hus
    -0.25
     cls
    -0.25
    \TestCase
    -0.24
    alars
    -0.24
    Ĭ
    -0.24
    POSITIVE LOGITS
     stand
    0.29
     lap
    0.29
    ZZ
    0.29
     rij
    0.27
     Lap
    0.27
     Mata
    0.27
    Pot
    0.26
    ban
    0.26
    ç«ĭ
    0.26
    icot
    0.26
    Activations Density 0.004%

    No Known Activations