© 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. 35325
    Prev
    Next
    INDEX
    Explanations

    months of the year

    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
    æ¯ıå¹´éĥ½
    -0.10
    æ¯ıå¹´
    -0.10
    羣æŃ£åģļåĪ°
    -0.10
     wÅĤaÅĽ
    -0.09
    æ½´
    -0.09
    å½ĵå¹´
    -0.09
    穹
    -0.09
    伺
    -0.09
     shorts
    -0.09
    åİĨå¹´
    -0.09
    POSITIVE LOGITS
    æĺ¨å¤©
    0.11
    è¿Ļåĩłå¤©
    0.11
    ä¸Ĭåij¨
    0.11
    æĺ¨æĹ¥
    0.10
    æĺ¨
    0.10
    è¿Ļ两天
    0.09
    举è¡ĮçļĦ
    0.09
    交ç»ĩ
    0.08
     Ø£Ùħس
    0.08
    åĨ³å®ļ
    0.08
    Activations Density 0.099%

    No Known Activations