© 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. 49314
    Prev
    Next
    INDEX
    Explanations

    defensive coordinator

    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
    bai
    -0.11
     zwar
    -0.10
     zunächst
    -0.10
    ðŁĩ¯
    -0.09
    âĹĪ
    -0.09
    â¼Ģ
    -0.09
    ìĻ
    -0.09
    éħŀ
    -0.09
    ⾬
    -0.09
    Êī
    -0.09
    POSITIVE LOGITS
    è¿Ļæīįæĺ¯
    0.11
    å±ĬæŶ
    0.10
    è¿ĶåĽŀæIJľçĭIJ
    0.09
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.08
    äºĨ解ä¸Ģä¸ĭ
    0.07
    çŃīçŃī
    0.07
    读åIJİæĦŁ
    0.07
    ç¬ĶèĢħ
    0.07
     TBD
    0.07
    ä¸ĭä¸Ģç¯ĩ
    0.07
    Activations Density 9.785%

    No Known Activations