© 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. 22415
    Prev
    Next
    INDEX
    Explanations

    ethylglyoxal

    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
    è¿ĻåĿĹ
    -0.10
    è´Ń
    -0.10
    åīª
    -0.09
    éĹ
    -0.09
    è¢į
    -0.09
    åĩ»
    -0.09
    翦
    -0.09
    æļĤæŶ
    -0.09
    æĹ¶æľº
    -0.08
    çĮ·
    -0.08
    POSITIVE LOGITS
    离èģĮ
    0.10
    责任
    0.10
    æĬ¼éĩij
    0.09
     Minor
    0.09
    æī¿æĭħ责任
    0.09
     деп
    0.09
    æŃ¥åħ¥
    0.08
    å½Ĵ
    0.08
    éķľåŃIJ
    0.08
    æľŁæľ«
    0.08
    Activations Density 0.030%

    No Known Activations