© 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. 47673
    Prev
    Next
    INDEX
    Explanations

    interesting / boring / challenging

    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
    Not in Any Lists

    No Comments

    Negative Logits
    é¢ľ
    -0.10
    çIJĨæĢ§
    -0.10
    æ¸ħéĻ¤
    -0.09
    秣
    -0.09
    ä¸ĢèĤ¡
    -0.09
    é¢ł
    -0.09
    зÑĭ
    -0.08
     situ
    -0.08
    ç«Ļéķ¿
    -0.08
    kers
    -0.08
    POSITIVE LOGITS
    æľī趣
    0.18
    æľī趣çļĦ
    0.18
    趣
    0.18
     инÑĤеÑĢеÑģ
    0.17
    趣åij³
    0.17
    _interest
    0.17
    åħ´è¶£
    0.16
    interesting
    0.16
     interest
    0.15
    æĹłèģĬ
    0.15
    Activations Density 0.091%

    No Known Activations