© 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. 24190
    Prev
    Next
    INDEX
    Explanations

    return to work

    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
    å°±æĺ¯è¿Ļæł·
    -0.09
    顺åĬ¿
    -0.08
    éĥ½åľ¨
    -0.08
    åĩºå±Ģ
    -0.08
    çļĩ
    -0.08
    kul
    -0.08
    nan
    -0.07
    就没æľī
    -0.07
    åĩºå¤Ħ
    -0.07
    å°±è¿ŀ
    -0.07
    POSITIVE LOGITS
    èī°èĭ¦
    0.12
    æľįåĬ¡è´¨éĩı
    0.12
     каÑĩеÑģÑĤво
    0.11
    çļĦè´¨éĩı
    0.11
    çĶ¨æĪ·ä½ĵéªĮ
    0.11
    åıįåĵį
    0.11
    ogh
    0.11
    å·¥ç¨ĭè´¨éĩı
    0.11
    åĩłçĤ¹
    0.11
    说å®ŀè¯Ŀ
    0.11
    Activations Density 0.302%

    No Known Activations