© 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. 12092
    Prev
    Next
    INDEX
    Explanations

    secret worlds

    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
     ë¬¼ë¡ł
    -0.09
    åıĺ为
    -0.08
    å§IJ妹
    -0.08
    æĸ°äºº
    -0.08
    inch
    -0.08
    çļĦæĪIJéķ¿
    -0.08
    éĻ¤äºĨ
    -0.08
    ä½łä¹Ł
    -0.08
    家åĽŃ
    -0.08
    ãĤĤãģ¡ãĤį
    -0.08
    POSITIVE LOGITS
    é³ĸ
    0.11
    è¿ĩçļĦ
    0.11
    å¤Ł
    0.10
    åıijå±ķçļĦ
    0.10
    yna
    0.10
    峤
    0.09
    çļĦè¯Ŀ
    0.09
    arez
    0.09
    BaseContext
    0.09
    inburgh
    0.09
    Activations Density 0.028%

    No Known Activations