© 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. 12364
    Prev
    Next
    INDEX
    Explanations

    deals with

    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
    Negative Logits
    ä¸ŃåĽ½åĽ½éĻħ
    -0.11
    æī«ä¸Ģæī«
    -0.11
    ä¸Ģ个好çļĦ
    -0.10
    缨
    -0.10
    åĬłå¼ºå¯¹
    -0.09
    ìķ½
    -0.09
    åłĩ
    -0.09
    æįº
    -0.09
    ÑīиÑĤ
    -0.09
     Rosenberg
    -0.09
    POSITIVE LOGITS
    è¿Ļ个éĹ®é¢ĺ
    0.12
    è¿Ļç§įæĥħåĨµ
    0.10
    è¿ĻäºĽéĹ®é¢ĺ
    0.09
    bars
    0.09
    çIJIJ
    0.09
    çĿ¬
    0.08
    ä¸į顾
    0.08
     Lal
    0.07
    ç»ĥ
    0.07
    éħįçĶµ
    0.07
    Activations Density 0.018%

    No Known Activations