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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3778
    Prev
    Next
    INDEX
    Explanations

    new people joining

    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
    .lazy
    -0.09
    modo
    -0.09
    幸
    -0.09
    иÑİ
    -0.09
     Caldwell
    -0.08
    åįķä¸Ģ
    -0.08
    éĤĢ
    -0.08
    æ±°
    -0.08
    åıijå±ķ模å¼ı
    -0.08
    itin
    -0.08
    POSITIVE LOGITS
    åĪ°æĿ¥
    0.11
    ä¸įäºĨ解
    0.10
    çļĦä¿¡å¿ĥ
    0.09
    bane
    0.09
     tô
    0.09
    åı°é£İ
    0.09
    äºŃ
    0.08
    ä¹Łæĺ¯éĿŀ常
    0.08
    ../../../
    0.08
    纳åħ¥
    0.08
    Activations Density 0.027%

    No Known Activations