© 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. 743
    Prev
    Next
    INDEX
    Explanations

    grammar and rules

    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
    translated
    -0.11
    è¯ij
    -0.11
     translated
    -0.10
    ç¿»è¯ij
    -0.10
    ترجÙħ
    -0.09
    ç¬Ļ
    -0.09
     пеÑĢевод
    -0.09
    Translations
    -0.09
     Schl
    -0.09
    gom
    -0.09
    POSITIVE LOGITS
    çĦī
    0.10
    utive
    0.09
    çŁ³åĮĸ
    0.09
    è§Ħ磩
    0.09
    Gram
    0.09
    lei
    0.08
    æ¸Ķ
    0.08
    æ½ĩæ´Ĵ
    0.08
    çĻ»ä¸Ĭ
    0.08
    çĤ¼
    0.08
    Activations Density 0.212%

    No Known Activations