© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 41145
    Prev
    Next
    INDEX
    Explanations

    access

    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
    vez
    -0.29
    achable
    -0.29
    CEL
    -0.29
    él
    -0.29
    aminer
    -0.28
     meta
    -0.28
    dist
    -0.27
    (meta
    -0.27
    -meta
    -0.27
    累累
    -0.27
    POSITIVE LOGITS
    ç©¿è¡£
    0.29
    ä¸įå¿į
    0.28
    rish
    0.28
    为ä»Ģä¹Īä¸į
    0.25
    re
    0.25
    icker
    0.25
    åıĪ好
    0.25
    .arguments
    0.25
    rin
    0.24
     charge
    0.24
    Activations Density 0.002%

    No Known Activations