© 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. 12-TRANSCODER-HP
    7. 22027
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    itations
    -0.25
    éŨ
    -0.24
    alysis
    -0.24
     çĻ»
    -0.24
    Mul
    -0.24
    ä¹ĺ
    -0.24
    onde
    -0.23
    itere
    -0.23
    onas
    -0.23
     Mul
    -0.23
    POSITIVE LOGITS
    导读
    0.26
    åĩºè¡Ģ
    0.26
    aug
    0.26
    нÑĭ
    0.26
    é«ĺ峰论åĿĽ
    0.24
    ä¿¡å¿ĥ
    0.24
    æł·æĿ¿
    0.24
     ÑĦоÑĢÑĥм
    0.24
    geb
    0.23
    论åĿĽ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.