© 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. 43508
    Prev
    Next
    INDEX
    Explanations

    pregnancy and medical research

    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
    cord
    -0.29
     associated
    -0.28
    è¡į
    -0.27
     bands
    -0.27
    bands
    -0.26
    stringValue
    -0.26
     Associated
    -0.26
    irst
    -0.25
    ĥģ
    -0.25
    å¯Ħ
    -0.25
    POSITIVE LOGITS
     Mate
    0.30
     Race
    0.29
    race
    0.28
    Race
    0.28
     race
    0.28
    à¤Ł
    0.27
    åħ»èĢģä¿ĿéĻ©
    0.27
    ô
    0.26
     critical
    0.26
    æıIJ
    0.25
    Activations Density 0.003%

    No Known Activations