© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63752
    Prev
    Next
    INDEX
    Explanations

    technical processes and tools

    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
    ished
    -0.10
    æľīæīĢ
    -0.10
    apped
    -0.10
    ized
    -0.09
    æ¶Īè´¹èĢħçļĦ
    -0.09
    åħ®
    -0.09
    (Function
    -0.09
    é¢ĨæĤŁ
    -0.09
    åĿIJä¸ĭ
    -0.09
    ä¿¡æģ¯å®īåħ¨
    -0.08
    POSITIVE LOGITS
    æľºåĪ¶
    0.19
     mechanism
    0.14
    æīĭ段
    0.14
    å·¥åħ·
    0.13
     mechanisms
    0.12
    æľįåĬ¡æľºæŀĦ
    0.11
    æĸ¹å¼ı
    0.11
     technique
    0.11
    åĪ©åĻ¨
    0.10
     tool
    0.10
    Activations Density 0.430%

    No Known Activations