© 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. 22098
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash
    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
     Mirror
    -0.28
    ksi
    -0.27
    Mirror
    -0.26
    éĵ¶
    -0.26
     mirror
    -0.26
    /fixtures
    -0.25
     reverse
    -0.25
     silver
    -0.25
    .Compose
    -0.25
    -inverse
    -0.25
    POSITIVE LOGITS
    æĿ¡ä»¶
    0.27
    uchs
    0.26
    éĹ³
    0.26
    haled
    0.26
    é¢Ĩ导ä¸ĭ
    0.26
    .newBuilder
    0.25
    代表æĢ§
    0.25
    _HAL
    0.25
    orra
    0.25
     leadership
    0.25
    Activations Density 0.001%

    No Known Activations