© 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. 47441
    Prev
    Next
    INDEX
    Explanations

    technical specifications and standards

    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
    ç´¯
    -0.09
    repid
    -0.08
    è¶ħ级
    -0.08
    çĭ®
    -0.08
    举æݪ
    -0.08
    è¶ħé¢Ŀ
    -0.08
    å®īä¸ľå°¼
    -0.08
    _accessible
    -0.08
    /fa
    -0.08
     Bord
    -0.08
    POSITIVE LOGITS
    æ·Ģ
    0.11
    åĴĮæľįåĬ¡
    0.09
    çıįçıł
    0.09
    çĤ¯
    0.09
     stall
    0.09
    车åĨħ
    0.09
    èįīæ¡Ī
    0.09
    åģľè½¦ä½į
    0.08
    æłĩè¯Ĩ
    0.08
    她æĺ¯
    0.08
    Activations Density 0.324%

    No Known Activations