© 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. 831
    Prev
    Next
    INDEX
    Explanations

    whether or if

    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¸ĮæľĽèĥ½
    -0.10
    èĥ½åģļåĪ°
    -0.10
    åĢ¼å¾Ĺ
    -0.09
    ä¿ĥ使
    -0.09
    .setInput
    -0.09
    æľīåı¯èĥ½
    -0.09
    /lic
    -0.09
    -motion
    -0.08
    赶
    -0.08
    åĽŀåIJĪ
    -0.08
    POSITIVE LOGITS
    åĬ¨
    0.09
    ëıĻ
    0.08
    论
    0.08
    éĿ¢åŃĶ
    0.08
    è¿ĩåİ»
    0.08
     cheek
    0.08
    hawk
    0.08
    æĺ¯éĿŀ
    0.08
    èij¬
    0.08
    åĩĨ
    0.08
    Activations Density 0.014%

    No Known Activations