© 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. 24320
    Prev
    Next
    INDEX
    Explanations

    Syracuse or Worcester

    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
    èĩªåıij
    -0.10
    /disable
    -0.09
    ä¾Ľæļĸ
    -0.09
    ìĤ°
    -0.09
    ihad
    -0.09
    inia
    -0.09
    æªIJ
    -0.08
     Äijáo
    -0.08
    ustr
    -0.08
    mor
    -0.08
    POSITIVE LOGITS
    alah
    0.09
    æľįåĬ¡ä½ĵç³»
    0.09
    ple
    0.09
     веÑī
    0.08
    WI
    0.08
    igli
    0.08
    èĤĦ
    0.08
    ãģ£ãģ¨
    0.08
    æĻ¦
    0.08
    éģŀ
    0.08
    Activations Density 0.002%

    No Known Activations