© 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. 16770
    Prev
    Next
    INDEX
    Explanations

    situation functionality

    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
    ottes
    -0.09
    har
    -0.09
    å©¿
    -0.09
    åIJĽåŃIJ
    -0.09
    æ¡ĥèĬ±
    -0.09
    åįĹéĺ³
    -0.08
    çĸĹç¨ĭ
    -0.08
    åħ¬çĽĬæĢ§
    -0.08
     кÑĢай
    -0.08
    .cleanup
    -0.08
    POSITIVE LOGITS
    anity
    0.10
    å¹³åĿĩæ¯ı
    0.10
    åĵĤ
    0.09
    鬼
    0.09
    ç½Ħ
    0.09
    åŁºæķ°
    0.08
    çļĦæķ°éĩı
    0.08
    unter
    0.08
    zag
    0.08
    clusive
    0.08
    Activations Density 0.978%

    No Known Activations