© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20495
    Prev
    Next
    INDEX
    Explanations

    but one or except for

    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
    ónica
    -0.10
    ä¼ĺè´¨
    -0.09
    æĥ¯
    -0.09
    æľĢå¿«çļĦ
    -0.09
    ä¸įåĬ¨
    -0.09
    屡
    -0.09
    éĢ¾
    -0.09
    åİĨ
    -0.09
    _GC
    -0.09
    å°±è¿Ļæł·
    -0.09
    POSITIVE LOGITS
    éĻ¤å¤ĸ
    0.11
     except
    0.10
    黾
    0.10
    çŁŃæļĤ
    0.09
    æľīåĩłä¸ª
    0.09
     dint
    0.09
    except
    0.09
    æ³ļ
    0.08
    åIJIJ
    0.08
     Pearl
    0.08
    Activations Density 0.077%

    No Known Activations