© 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. 42470
    Prev
    Next
    INDEX
    Explanations

    uck

    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
    edo
    -0.34
    èµ°åIJij
    -0.27
    dale
    -0.25
    èĹ©
    -0.25
    aldo
    -0.25
     Tanks
    -0.25
    Bow
    -0.24
    åĴ©
    -0.24
    edio
    -0.24
    ardy
    -0.24
    POSITIVE LOGITS
     upside
    0.28
     convict
    0.26
     seven
    0.25
     Melissa
    0.25
    -h
    0.25
     hitting
    0.25
    é¡Į
    0.24
     seventeen
    0.24
    y
    0.24
     successive
    0.24
    Activations Density 0.001%

    No Known Activations