© 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. 31362
    Prev
    Next
    INDEX
    Explanations

    in [locations]

    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¿ijæľŁ
    -0.15
    è¿ĻäºĽå¹´
    -0.15
    è¿ijæĹ¥
    -0.15
     recent
    -0.14
    å¤ļå¹´æĿ¥
    -0.14
    è¿ijå¹´æĿ¥
    -0.14
    è¿ijäºĽå¹´
    -0.13
    è¿ijåĩłå¹´
    -0.13
    è¿Ļä¹Īå¤ļå¹´
    -0.13
    è¿ijå¹´
    -0.13
    POSITIVE LOGITS
    ä¸įå°ıçļĦ
    0.09
    é£İåIJ¹
    0.09
    agna
    0.09
    å©Ĩ
    0.08
    å¦Ĥæŀľä¸įæĺ¯
    0.08
    身ä½ĵåģ¥åº·
    0.08
    æīĢè°ĵçļĦ
    0.08
    ç»Ļ人
    0.08
    书æĪ¿
    0.08
    ä»ħ次äºİ
    0.08
    Activations Density 0.239%

    No Known Activations