© 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. 3120
    Prev
    Next
    INDEX
    Explanations

    any kind/purpose

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æīİ
    -0.09
    å¥ĸéĩij
    -0.08
    æ±Łæ·®
    -0.08
     Denis
    -0.08
    ius
    -0.08
     ÑĢемонÑĤ
    -0.08
    赡
    -0.08
    anna
    -0.08
    éĶĻ
    -0.08
    缩
    -0.08
    POSITIVE LOGITS
    没æľīå¿ħè¦ģ
    0.10
    ä¸ĢåŃĹ
    0.09
    è¿Ļåıª
    0.09
    举起
    0.09
    游ä¹IJ
    0.08
    妹åŃIJ
    0.08
    _friend
    0.08
    ä»ħ次äºİ
    0.08
    ä¸ĭçıŃ
    0.08
    _variation
    0.08
    Activations Density 0.034%

    No Known Activations