© 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. 27-TRANSCODER-HP
    7. 9754
    Prev
    Next
    INDEX
    Explanations

    dynamic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    壹
    -0.25
    æı¡æīĭ
    -0.24
    åĭĴ
    -0.23
     fprintf
    -0.23
     vaz
    -0.23
     nbytes
    -0.23
    wend
    -0.23
    殿
    -0.22
    ohen
    -0.22
    泡沫
    -0.22
    POSITIVE LOGITS
    åĬ¨æĢģ
    1.27
     dynamic
    1.17
    dynamic
    0.98
     Dynamic
    0.93
     dynamics
    0.91
    åĬ¨æĦŁ
    0.90
     dynam
    0.90
    Dynamic
    0.88
    (dynamic
    0.87
    _dynamic
    0.85
    Activations Density 0.001%

    No Known Activations