© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6897
    Prev
    Next
    INDEX
    Explanations

    so much

    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
    ì§ģ
    -0.10
    гоÑĢ
    -0.09
     Ñĩем
    -0.09
    ä¸ĢåŃĹ
    -0.09
    ä»ģ
    -0.09
    éĢIJæ¸IJ
    -0.09
    趣
    -0.08
    é¦Ĵ头
    -0.08
    æ£Ģ
    -0.08
    æ¸IJæ¸IJ
    -0.08
    POSITIVE LOGITS
    è¿Ļä¹Īå¤ļ
    0.26
    å¦ĤæѤ
    0.24
    éĤ£ä¹Īå¤ļ
    0.23
    è¿Ļä¹Ī
    0.23
    è¿Ļä¹Ī大
    0.22
    éĤ£ä¹Ī
    0.20
    è¿Ļä¹Īä¹ħ
    0.19
    éĤ£éº¼
    0.18
    éĢĻ麼
    0.18
    éĤ£ä¹Ī容æĺĵ
    0.17
    Activations Density 0.067%

    No Known Activations