© 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. 43798
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    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
     badges
    -0.27
    opoulos
    -0.26
    夺
    -0.26
    ement
    -0.26
    igu
    -0.26
    串
    -0.26
    NR
    -0.24
    ading
    -0.24
     Nou
    -0.24
     Mane
    -0.24
    POSITIVE LOGITS
    ({_
    0.26
     pragma
    0.26
    elts
    0.26
     fry
    0.26
     barracks
    0.25
     Commission
    0.25
    ly
    0.25
     dr
    0.24
    ursal
    0.24
    borg
    0.24
    Activations Density 0.000%

    No Known Activations