© 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. 24202
    Prev
    Next
    INDEX
    Explanations

    processing

    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
    æĶĴ
    -0.29
    è´´
    -0.29
    (IServiceCollection
    -0.28
     closets
    -0.28
     universities
    -0.26
     instantaneous
    -0.26
    è²¼
    -0.26
     instantiation
    -0.26
    bolt
    -0.25
     politics
    -0.25
    POSITIVE LOGITS
    åĮĹç¾İ
    0.27
     ÑĤÑĢав
    0.27
    æīŃæĽ²
    0.27
    _instructions
    0.27
    åľ°ä¸ĭæ°´
    0.27
    пÑĥÑĤ
    0.26
     Burton
    0.26
    .instructions
    0.26
    奴éļ¶
    0.25
    çľ¼åīį
    0.25
    Activations Density 0.004%

    No Known Activations