© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22319
    Prev
    Next
    INDEX
    Explanations

    asked me

    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
    chine
    -0.10
    æīĢ以æĪij
    -0.09
    éģĤ
    -0.09
    广大群ä¼Ĺ
    -0.09
    è¿Ļéĥ¨åĪĨ
    -0.09
    æīĢ以æĪij们
    -0.09
    æľīä¸Ģå®ļçļĦ
    -0.09
    леж
    -0.09
    äºİæĺ¯æĪij
    -0.08
    使å¾Ĺ
    -0.08
    POSITIVE LOGITS
    ald
    0.09
    æĹłè®ºå¦Ĥä½ķ
    0.09
    rown
    0.09
    about
    0.09
     why
    0.08
     about
    0.08
    åģ¥
    0.08
    ä¸įè¦ģ
    0.08
     Dias
    0.08
    è°İ
    0.08
    Activations Density 0.018%

    No Known Activations