© 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. 22925
    Prev
    Next
    INDEX
    Explanations

    judging and legal behavior

    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
     ترÙĥ
    -0.09
    æ³¥
    -0.09
     SYNC
    -0.09
    é¹ij
    -0.09
     chi
    -0.09
     spyOn
    -0.09
    ä¸įåIJĪçIJĨ
    -0.08
    å¿ħä¸įåı¯
    -0.08
    itemap
    -0.08
    æľīä»·åĢ¼
    -0.08
    POSITIVE LOGITS
    审çIJĨ
    0.12
    æ³ķå®ĺ
    0.12
    审åĪ¤
    0.11
     courtroom
    0.11
    åºŃ审
    0.10
    æī§æ³ķ
    0.10
    åħ¬æŃ£
    0.10
    åĬŀæ¡Ī
    0.10
    å±¥èģĮ
    0.09
     اÙĦÙĤض
    0.09
    Activations Density 0.085%

    No Known Activations