© 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. 52267
    Prev
    Next
    INDEX
    Explanations

    up and running

    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
    aton
    -0.09
    باب
    -0.09
    à¹ģà¸ľ
    -0.09
    ÄŁi
    -0.08
    æŃ¥æŃ¥
    -0.08
    大夫
    -0.08
    ught
    -0.08
    ult
    -0.08
     Hamp
    -0.08
    æīĢå±ŀ
    -0.08
    POSITIVE LOGITS
    mond
    0.10
    åŃļ
    0.09
    ç»ıå¼Ģ
    0.09
    åľ¨æ¸¸æĪıä¸Ń
    0.09
    èĢħçļĦ
    0.09
    å«Ĥ
    0.09
    indle
    0.09
    çĶ¨å¾®ä¿¡
    0.09
    land
    0.09
    è¿IJèIJ¥ç®¡çIJĨ
    0.08
    Activations Density 0.027%

    No Known Activations