© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22625
    Prev
    Next
    INDEX
    Explanations

    levels of skill and improvement

    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
    eka
    -0.10
    è¿¢
    -0.10
    èĤłéģĵ
    -0.09
    ç½į
    -0.09
    fait
    -0.08
    çŃļ
    -0.08
    éĤĪ
    -0.08
     Vibr
    -0.08
     Gamer
    -0.08
    ahir
    -0.08
    POSITIVE LOGITS
    æ°´å¹³
    0.12
    æĬĢèīº
    0.11
    è¿ĽæŃ¥
    0.11
    é¢ĨæĤŁ
    0.10
    é¢Ĩä¼ļ
    0.10
    æıIJé«ĺ
    0.10
     improvement
    0.10
    ç²¾æ¹Ľ
    0.10
     improving
    0.10
     Improve
    0.10
    Activations Density 0.254%

    No Known Activations