© 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. 12396
    Prev
    Next
    INDEX
    Explanations

    spices and flavours

    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
    ìĥ·
    -0.09
    çµ®
    -0.09
    缮çļĦ
    -0.09
    è§Ĥæij©
    -0.09
    èı
    -0.09
    åĽº
    -0.09
    ç¥Ŀ
    -0.09
    çºłç¼ł
    -0.09
    apiro
    -0.09
    _HT
    -0.09
    POSITIVE LOGITS
    çļĦåij³éģĵ
    0.10
    onor
    0.09
    举åįĹäºļ
    0.09
    éĹ»
    0.08
    æĬĵ
    0.08
    æĢ¯
    0.08
     SOS
    0.08
    _deep
    0.08
    æīĴ
    0.08
     cuis
    0.08
    Activations Density 0.058%

    No Known Activations