© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8068
    Prev
    Next
    INDEX
    Explanations

    motoGP, rally, rider, manufacturing

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ogn
    -0.09
    解æķ£
    -0.09
    æĴĩ
    -0.09
    æĥ³èµ·æĿ¥
    -0.08
    æĺ¯éŁ©åĽ½
    -0.08
    ç¼ĸåı·
    -0.08
    é¦į
    -0.08
    彧
    -0.08
    æĢİ
    -0.08
    ä¸Ģ个æĺŁæľŁ
    -0.08
    POSITIVE LOGITS
    crest
    0.09
    éŀį
    0.09
    éªijè¡Į
    0.09
    åľ¨è·¯ä¸Ĭ
    0.08
    riding
    0.08
    allas
    0.08
     Trey
    0.08
    ä¼Ĭæĭī
    0.08
    æij©æīĺ
    0.08
    ilent
    0.08
    Activations Density 0.052%

    No Known Activations