© 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. 55461
    Prev
    Next
    INDEX
    Explanations

    that of

    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
    æĹħ
    -0.09
    atory
    -0.09
    bero
    -0.09
    anus
    -0.09
     Trip
    -0.08
    æŃ¦å£«
    -0.08
    ivism
    -0.08
    ãģĵãĤĮãģĮ
    -0.08
    èIJ¥
    -0.08
    åīĸ
    -0.08
    POSITIVE LOGITS
    à¸Ĵ
    0.09
    继
    0.09
    ç¹¼
    0.09
    ä¼Łå¤§
    0.09
    ORK
    0.09
    继ç»Ńä¿ĿæĮģ
    0.09
    ÙĨØ´
    0.09
    éĹ´çļĦ
    0.09
    éĶ¦
    0.08
     ÑģÑĤоим
    0.08
    Activations Density 0.028%

    No Known Activations