© 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. 18940
    Prev
    Next
    INDEX
    Explanations

    on the rise

    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
    ÙĤض
    -0.11
    ä½ĵåĨħ
    -0.09
    é³
    -0.09
    ç»Ĩ
    -0.09
    鸣
    -0.08
    å¸Ĥåľºä¸»ä½ĵ
    -0.08
    äºĮ线
    -0.08
    åĪ¤
    -0.08
    æķĻåŃ¦è´¨éĩı
    -0.08
    XA
    -0.08
    POSITIVE LOGITS
    ä¸ĭéĻį
    0.11
     lanc
    0.09
     declined
    0.09
    æĭ¾
    0.09
    ä¸Ĭåįĩ
    0.09
    å¾ĺå¾Ĭ
    0.09
    otec
    0.09
    æ¾¹
    0.09
    å·²åľ¨
    0.09
    éĶIJ
    0.08
    Activations Density 0.086%

    No Known Activations