© 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. 24112
    Prev
    Next
    INDEX
    Explanations

    over + related words

    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
    æ³¼
    -0.10
    åıĺéĢŁ
    -0.09
     jud
    -0.09
    鸱
    -0.09
    åĪĨæĺİ
    -0.09
     Alo
    -0.09
    æı´
    -0.09
    æįŁ
    -0.09
    .ObjectModel
    -0.08
    åħ¼
    -0.08
    POSITIVE LOGITS
    åĿİ
    0.10
    ä¸Ī夫
    0.08
    åıijå±ķéĺ¶æ®µ
    0.08
    ä¼Ĭ
    0.08
    è´·
    0.08
    ters
    0.08
    Impossible
    0.07
    æ®ī
    0.07
    ugar
    0.07
    æİĮ
    0.07
    Activations Density 0.011%

    No Known Activations