© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47648
    Prev
    Next
    INDEX
    Explanations

    second delay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    çŁŃæľŁ
    -0.10
    datepicker
    -0.10
    çŁŃæľŁåĨħ
    -0.10
    æĹ¥å¤ľ
    -0.10
    çªł
    -0.10
    讽
    -0.10
    å¯Ħæīĺ
    -0.10
     Overnight
    -0.09
    åīĬ
    -0.09
    imax
    -0.09
    POSITIVE LOGITS
    ä¸Ģç§Ĵ
    0.16
    ç§Ĵ
    0.13
     seconds
    0.12
    ä¸ĢåĪĨéĴŁ
    0.11
    ç§ĴéĴŁ
    0.11
    .seconds
    0.10
    seconds
    0.10
    çīĩåĪ»
    0.10
    æģ¯
    0.10
    secs
    0.09
    Activations Density 0.079%

    No Known Activations