© 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. 26307
    Prev
    Next
    INDEX
    Explanations

    on offense

    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
    umb
    -0.09
    ç²¾ç¥ŀ
    -0.09
    ANGLE
    -0.09
    æ§Ľ
    -0.09
    è°IJ
    -0.09
    ละ
    -0.08
    è£Ĩ
    -0.08
     новÑĭе
    -0.08
    è¯Ŀ
    -0.08
    çļĦçľ¼
    -0.08
    POSITIVE LOGITS
    åĽº
    0.10
    ç´«èī²
    0.10
    éļİ
    0.09
    ucker
    0.09
    _SCL
    0.08
    åĿı
    0.08
    ç»Ħ建
    0.08
    haar
    0.08
    å¢Ģ
    0.08
    hand
    0.08
    Activations Density 0.021%

    No Known Activations