© 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. 24090
    Prev
    Next
    INDEX
    Explanations

    height measurements

    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
    æ±ł
    -0.08
    åĺ´
    -0.08
    æŁĦ
    -0.07
    ENCH
    -0.07
    åĬ£
    -0.07
    agers
    -0.07
    ç¾½
    -0.07
    è¶Ĭ
    -0.07
    ä»İæĿ¥
    -0.07
    éĥ¨å§Ķ
    -0.07
    POSITIVE LOGITS
    ä¸Ģ大åłĨ
    0.12
    edly
    0.09
    ä¸Ģç¯ĩ
    0.09
    å¯Į
    0.09
    饴
    0.09
    å°¬
    0.09
    ëĮĵ
    0.09
    漪
    0.09
     Sticky
    0.09
    æ¿¡
    0.09
    Activations Density 0.031%

    No Known Activations