© 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. 63871
    Prev
    Next
    INDEX
    Explanations

    association between

    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
    ãģ»ãģ©
    -0.10
    ç»ıæµİåŃ¦å®¶
    -0.10
    åĽĽæĸ¹
    -0.09
    对ç«ĭ
    -0.09
    oise
    -0.09
    ç¦ģå¿Į
    -0.09
    ependency
    -0.08
     Enough
    -0.08
    ingu
    -0.08
    eful
    -0.08
    POSITIVE LOGITS
    è´¨éĩıåĴĮ
    0.09
    illet
    0.09
    好好
    0.09
     è¾
    0.08
    åĪ°ä½į
    0.08
    (s
    0.08
    amba
    0.08
    è¿Ļ段
    0.08
    æĸĹ
    0.08
     MAS
    0.08
    Activations Density 0.110%

    No Known Activations