© 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. 16914
    Prev
    Next
    INDEX
    Explanations

    saw this

    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
    éĴĬ
    -0.09
    çļĦéŃħåĬĽ
    -0.09
    ä½ĵéªĮ
    -0.09
    æ¾ľ
    -0.08
     Rak
    -0.08
    æ¼Ĥ
    -0.08
    纹çIJĨ
    -0.08
    ç·Ĭ
    -0.08
    çľ¼çļ®
    -0.08
    itime
    -0.08
    POSITIVE LOGITS
    æĬ¥éģĵ
    0.13
     headlines
    0.11
    åªĴä½ĵæĬ¥éģĵ
    0.11
    çľĭåĪ°
    0.10
    åıªä¼ļ
    0.10
    æĸ°éĹ»
    0.10
    åIJ¬åĪ°
    0.09
    atum
    0.09
    æĬ¥éģĵ称
    0.09
     pictures
    0.09
    Activations Density 0.091%

    No Known Activations