© 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. 50226
    Prev
    Next
    INDEX
    Explanations

    after all

    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
    è·ŁæĪij
    -0.10
    è°Ĺ
    -0.09
    大éĿ¢ç§¯
    -0.09
    AAP
    -0.09
     Epstein
    -0.09
    uly
    -0.09
    alles
    -0.09
     Nes
    -0.09
    èī°
    -0.09
    å´´
    -0.09
    POSITIVE LOGITS
    çķ¢ç«Ł
    0.13
    æ¯ķç«Ł
    0.12
    æ¯ķç«Łæĺ¯
    0.12
    éĤ£ä¹Ī容æĺĵ
    0.10
    ä½ķåĨµ
    0.10
    æĽ´ä½ķåĨµ
    0.09
    æľ¬èº«å°±æĺ¯
    0.09
    æĪIJåĬŁçļĦ
    0.09
    åĺĽ
    0.09
     already
    0.08
    Activations Density 0.051%

    No Known Activations