© 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. 24222
    Prev
    Next
    INDEX
    Explanations

    once something is ready

    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
    å¾Īå¿«
    -0.13
    ä»İæѤ
    -0.12
    å¾Īå¿«å°±
    -0.11
    æĪij们çİ°åľ¨
    -0.11
    åIJ¦
    -0.10
    èĩªæѤ
    -0.10
    æĪijçİ°åľ¨
    -0.10
    æĪijä»¬åľ¨
    -0.10
    å½ĵæŶ
    -0.09
    æĪijå½ĵæŶ
    -0.09
    POSITIVE LOGITS
    ä¸įåĨį
    0.11
    åIJİåĨį
    0.10
    积累
    0.09
    建ç«ĭèµ·
    0.09
    çľī
    0.09
    ä¸įåĨįæĺ¯
    0.09
    便åı¯
    0.09
    nod
    0.09
    为æŃ¢
    0.09
    交ä¼ļ
    0.09
    Activations Density 0.219%

    No Known Activations