© 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. 40846
    Prev
    Next
    INDEX
    Explanations

    make

    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
    Negative Logits
     most
    -0.42
    ä¸ŃæľĢ
    -0.39
     Most
    -0.38
    most
    -0.35
    Most
    -0.33
    _most
    -0.31
    -most
    -0.31
    stab
    -0.30
    æľĢ
    -0.29
    MOST
    -0.29
    POSITIVE LOGITS
    udies
    0.28
    åģ¥åº·
    0.27
    trs
    0.26
     health
    0.26
     oppressed
    0.26
    ãģĬé¡ĺãģĦ
    0.25
     responsible
    0.25
     families
    0.25
     societies
    0.24
     healthy
    0.24
    Activations Density 0.003%

    No Known Activations