© 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. 44044
    Prev
    Next
    INDEX
    Explanations

    thinking

    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
     explicit
    -0.28
    æĸĻ
    -0.28
    :first
    -0.26
    顯
    -0.25
     First
    -0.25
    ewn
    -0.25
    areth
    -0.24
    第ä¸Ģ
    -0.24
     ilk
    -0.24
     Voll
    -0.24
    POSITIVE LOGITS
    hum
    0.33
    ä¸ĢåĽŀäºĭ
    0.26
    scope
    0.26
    (scope
    0.26
    gresql
    0.26
     scope
    0.25
    Hum
    0.25
    æ´»çĿĢ
    0.25
    switch
    0.24
    (dead
    0.24
    Activations Density 0.000%

    No Known Activations