© 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. 26201
    Prev
    Next
    INDEX
    Explanations

    just so happens to

    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
    å¥ł
    -0.10
    ç½Ķ
    -0.09
    CDATA
    -0.09
    è¢ħ
    -0.09
    elly
    -0.09
    æĥķ
    -0.09
    éĹ®
    -0.09
    elts
    -0.09
    é«ĺä½İ
    -0.09
    elle
    -0.09
    POSITIVE LOGITS
    æģ°å¥½
    0.16
    å·§åIJĪ
    0.15
    æģ°
    0.14
    åĪļ好
    0.13
    å·§
    0.12
     coincidence
    0.11
     coinc
    0.11
    æŃ£å¥½
    0.10
    赶ä¸Ĭ
    0.10
    身为
    0.10
    Activations Density 0.020%

    No Known Activations