© 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. 47562
    Prev
    Next
    INDEX
    Explanations

    more like

    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
    驾çħ§
    -0.09
    æĽ´é«ĺçļĦ
    -0.08
    (seg
    -0.08
    ãģĦãģ¾ãģĻ
    -0.08
    çīĮåŃIJ
    -0.08
    åıªçŁ¥éģĵ
    -0.08
    ONLY
    -0.08
    çĭŃçªĦ
    -0.08
    tri
    -0.08
    abis
    -0.08
    POSITIVE LOGITS
    _IND
    0.09
    è¿Ļæł·æīįèĥ½
    0.09
    éĿł
    0.09
     niż
    0.09
    è´¨
    0.09
     Lime
    0.09
    欧ç¾İ
    0.09
    olf
    0.09
     than
    0.08
     xuyên
    0.08
    Activations Density 0.172%

    No Known Activations