© 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. 44191
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Tr
    -0.26
    osa
    -0.26
    ä¸įæ¸ħ
    -0.26
    apol
    -0.26
    gis
    -0.25
    freeze
    -0.25
    æķ£åıij
    -0.25
    leta
    -0.24
     tr
    -0.24
    autical
    -0.24
    POSITIVE LOGITS
    ç»Ļ
    0.28
    åŁ
    0.26
    Dire
    0.24
    pike
    0.24
    ERY
    0.24
    é¦ĸè½®
    0.24
    uner
    0.24
     recovered
    0.23
    ario
    0.23
    ientes
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.