© 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. 59440
    Prev
    Next
    INDEX
    Explanations

    telegrams, telematics, teleservice, telehealth, televisions

    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
    yx
    -0.09
    ìĪ
    -0.08
    æīĵçł´
    -0.08
    ECT
    -0.08
    onis
    -0.08
    åŁ¹èĤ²
    -0.08
    ä¸Ģä¸ĭ
    -0.08
    æĥ¯
    -0.08
    认å®ļ
    -0.08
     Pieces
    -0.08
    POSITIVE LOGITS
    .tel
    0.10
    è¯Ŀ
    0.09
    éĤ£ä¹Īç®Ģåįķ
    0.09
    еÑĪ
    0.09
    jer
    0.09
    æĿijæ°ij们
    0.09
    çĻ½é©¬
    0.09
    æŸ
    0.08
    äºĭä¸ļ
    0.08
    íħĶ
    0.08
    Activations Density 0.039%

    No Known Activations