© 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. 58479
    Prev
    Next
    INDEX
    Explanations

    the

    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
    åĬŁ
    -0.31
     swell
    -0.30
    çļĦéŃħåĬĽ
    -0.28
    беÑĢ
    -0.28
    çļĦæīĢæľī
    -0.27
     swelling
    -0.26
     US
    -0.26
     sw
    -0.26
    기를
    -0.25
    ber
    -0.24
    POSITIVE LOGITS
     detain
    0.29
    æĿ¯
    0.28
    _stdio
    0.27
    robot
    0.25
    æıŃ示
    0.25
     Plates
    0.25
    å¹³éĿ¢
    0.25
     plates
    0.25
    yleft
    0.25
    ooter
    0.24
    Activations Density 0.001%

    No Known Activations