© 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. 47626
    Prev
    Next
    INDEX
    Explanations

    only when available

    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
     Trot
    -0.09
     Lug
    -0.08
    çĥŃæĥħ
    -0.08
    SSL
    -0.08
    å¿ĥæĥ³
    -0.08
    ÑĮе
    -0.08
     isl
    -0.07
    ÑģÑĤÑĢ
    -0.07
    æ°ijéĹ´
    -0.07
     hier
    -0.07
    POSITIVE LOGITS
    ä¹Łåıªæľī
    0.13
    éĢĤçĶ¨äºİ
    0.12
    åıªæľī
    0.12
    éĢĤçĶ¨
    0.11
     only
    0.11
    åĩºçİ°åľ¨
    0.11
    åıª
    0.11
     ÙģÙĤØ·
    0.11
    åŃĺåľ¨äºİ
    0.11
    çī¹å®ļ
    0.11
    Activations Density 0.242%

    No Known Activations