© 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. 12399
    Prev
    Next
    INDEX
    Explanations

    reviewing and rating

    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
    еÑģÑĤво
    -0.09
    æĿł
    -0.09
    subs
    -0.09
    æ¦Ħ
    -0.09
    lock
    -0.09
    ofs
    -0.08
    oram
    -0.08
    å»īæ´ģ
    -0.08
    spl
    -0.08
    蹩
    -0.08
    POSITIVE LOGITS
    æĻĴ
    0.10
    浯
    0.09
    éĹ¾
    0.09
    读åIJİ
    0.08
     Toys
    0.08
     russian
    0.08
     Sey
    0.08
    earned
    0.08
    å¥Ĺè£ħ
    0.08
    æīĵ好
    0.08
    Activations Density 0.013%

    No Known Activations