© 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. 64090
    Prev
    Next
    INDEX
    Explanations

    daily digest

    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
    çĶ·åŃIJ
    -0.12
    éĻį
    -0.10
    æ¯ķ
    -0.10
    æľĪä¸ĭ
    -0.09
    æīĵåĩº
    -0.09
    ç¥Ľ
    -0.09
    åĬ¨åijĺ
    -0.09
    åħijæį¢
    -0.08
    æĬĢæ³ķ
    -0.08
    èµŃ
    -0.08
    POSITIVE LOGITS
    æ¯ıæĹ¥
    0.15
    æ¯ı天
    0.13
     daily
    0.12
    Daily
    0.11
    .digest
    0.11
    æĸ°éĹ»
    0.11
     Daily
    0.11
    daily
    0.10
    æĻ¨
    0.10
    digest
    0.10
    Activations Density 0.110%

    No Known Activations