© 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. 12249
    Prev
    Next
    INDEX
    Explanations

    no matter what

    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
    æĪIJçĨŁ
    -0.09
     Cup
    -0.08
    åŃ°
    -0.08
    صر
    -0.08
    åIJįåı«
    -0.08
    alta
    -0.08
     Nob
    -0.08
    大æ¦Ĥ
    -0.08
    Incre
    -0.08
    è¿Ļç§į
    -0.08
    POSITIVE LOGITS
    éľ¾
    0.10
    é£İ鼨
    0.10
    é¼¾
    0.10
    åħ¶ä»ĸ人
    0.10
    å¶Ļ
    0.10
    éĽĴ
    0.09
    è¹ĩ
    0.09
    èµ°åħ¥
    0.09
    ä¹¾åĿ¤
    0.09
    ather
    0.09
    Activations Density 0.023%

    No Known Activations