© 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. 63893
    Prev
    Next
    INDEX
    Explanations

    northernmost, southernmost, furthest, end

    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
    åħļåĴĮåĽ½å®¶
    -0.10
    çĽ¸äº²
    -0.10
    讳
    -0.09
    çŁŃæļĤ
    -0.09
    åķĨåľº
    -0.09
    缸åĬ©
    -0.09
    åĨįçİ°
    -0.09
    ç§ģä¸ĭ
    -0.09
    çļĦåİĭåĬĽ
    -0.08
    ä¸ĭåįĬ
    -0.08
    POSITIVE LOGITS
    åľ¨å¤ĸ
    0.12
     кÑĢай
    0.11
    è¾¹ç¼ĺ
    0.11
    è¿ľ
    0.11
    Extreme
    0.11
    æľ«ç«¯
    0.11
    è¿ľç¦»
    0.11
    far
    0.11
    éģIJ
    0.10
    åģıè¿ľ
    0.10
    Activations Density 0.148%

    No Known Activations