© 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. 16758
    Prev
    Next
    INDEX
    Explanations

    work and effort

    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
    çİ°åŃĺ
    -0.11
    apur
    -0.09
    å°¼æĸ¯
    -0.09
    å´´
    -0.09
     absor
    -0.09
    éĻ©
    -0.08
    _FUN
    -0.08
    atural
    -0.08
    issues
    -0.08
    æįŁ
    -0.08
    POSITIVE LOGITS
    åĬ³åĬ¨
    0.15
    æ±Ĺæ°´
    0.13
    åĭŀ
    0.13
    ä»ĺåĩº
    0.12
    è¾Ľåĭ¤
    0.12
    çļĦåĬªåĬĽ
    0.12
    åĭ¤åĬ³
    0.12
    èĢķèĢĺ
    0.11
    è¾Ľ
    0.11
    è¾Ľèĭ¦
    0.11
    Activations Density 0.028%

    No Known Activations