© 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. 860
    Prev
    Next
    INDEX
    Explanations

    part of

    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
    æĢ»ä½ĵ
    -0.09
    çŁ³
    -0.08
    asel
    -0.08
     Det
    -0.08
    usercontent
    -0.08
     Vend
    -0.08
     Abb
    -0.08
    æĢ¦
    -0.08
    aney
    -0.08
    HEEL
    -0.07
    POSITIVE LOGITS
    åıijåĬ¨
    0.10
    æĺ¯æĪij们
    0.09
    ä¸ŃåĽ½å¸Ĥåľº
    0.09
    åĬ¬
    0.09
    ä¸ĢæĹı
    0.09
    massage
    0.09
    æľĭ
    0.08
    aking
    0.08
    icularly
    0.08
    ä¼ļ对
    0.08
    Activations Density 0.026%

    No Known Activations