© 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. 24072
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions

    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
    çĤ¬
    -0.10
    æĪijåİ»
    -0.10
    anni
    -0.09
     nằm
    -0.08
    åIJ¬å®Į
    -0.08
    åIJĦç§įåIJĦæł·
    -0.08
    robots
    -0.08
    ini
    -0.08
    uard
    -0.08
    .uf
    -0.08
    POSITIVE LOGITS
    æ·¡
    0.10
    åŁĴ
    0.08
    èŁĴ
    0.08
    æıIJçĤ¼
    0.08
    åı¯æĥ³
    0.08
    èģĶç³»æĸ¹å¼ı
    0.08
    æ±Ģ
    0.08
    ä½Ĩçİ°åľ¨
    0.08
    stell
    0.07
    èĸĦå¼±
    0.07
    Activations Density 0.036%

    No Known Activations