© 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. 24286
    Prev
    Next
    INDEX
    Explanations

    role of

    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
    lâ
    -0.10
    ãģĹãģ¾ãģĨ
    -0.10
    ry
    -0.10
    à¹ĥà¸Ī
    -0.09
    rale
    -0.09
    ÑĮÑı
    -0.09
    dom
    -0.09
    antha
    -0.09
    lay
    -0.09
     Klein
    -0.09
    POSITIVE LOGITS
    fully
    0.13
    æī®æ¼Ķ游æĪı
    0.11
    ondon
    0.10
    lessness
    0.10
    ful
    0.10
    ationship
    0.10
    itim
    0.09
    leston
    0.09
    aina
    0.09
    letes
    0.09
    Activations Density 0.044%

    No Known Activations