© 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. 39077
    Prev
    Next
    INDEX
    Explanations

    awards and rankings

    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
    éĤĪ
    -0.09
    нем
    -0.08
    稷
    -0.08
    bon
    -0.08
     swe
    -0.08
     заÑı
    -0.08
    ç©©
    -0.08
    æģ©
    -0.08
    æijĩ
    -0.08
    ICH
    -0.08
    POSITIVE LOGITS
    é¹Ħ
    0.10
    arius
    0.10
    åĢ¼å¾Ĺåħ³æ³¨
    0.10
     buen
    0.09
    åįģ大
    0.09
    天ä¸ĭ
    0.08
     Heller
    0.08
    omat
    0.08
    TestCase
    0.08
    éĺ»ç¢į
    0.08
    Activations Density 0.074%

    No Known Activations