© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50495
    Prev
    Next
    INDEX
    Explanations

    first number

    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
    æľ¬èº«çļĦ
    -0.10
    峡
    -0.09
    åħ¨åľº
    -0.09
    æľ¬èº«
    -0.09
    æľ¬èº«å°±æĺ¯
    -0.09
     entire
    -0.09
    çļĦåIJĦç§į
    -0.08
    ä¸ĸçķĮä¸ĬæľĢ
    -0.08
    éĤ£æł·
    -0.08
    avin
    -0.08
    POSITIVE LOGITS
    ç¼Ģ
    0.11
    æĹ¥åŃIJ
    0.09
    éĵ¤
    0.09
    ä¹Łéĥ½
    0.09
    ä¸Ģçľ¼
    0.08
    裨
    0.08
    åħ«åį¦
    0.08
    æĥħåĨµæĿ¥çľĭ
    0.08
    磼
    0.08
    çŁ¿ä¸ļ
    0.08
    Activations Density 0.067%

    No Known Activations