© 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. 62363
    Prev
    Next
    INDEX
    Explanations

    separate or different instances

    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
    isse
    -0.09
    好象
    -0.09
    urat
    -0.09
    æĸ°å½¢åĬ¿ä¸ĭ
    -0.09
    æĽ´å¤ļä¿¡æģ¯
    -0.09
    .quick
    -0.08
     (*((
    -0.08
    overview
    -0.08
    aman
    -0.08
    uggling
    -0.08
    POSITIVE LOGITS
    ä¸įåIJĮçļĦ
    0.11
    秦çļĩ
    0.10
    åĽŀäºĭ
    0.10
     occasions
    0.10
    åľºåIJĪ
    0.10
    æ°§åĮĸ
    0.09
    å¼Ģè¾Ł
    0.09
    æĤ²åī§
    0.09
    åĺ¿
    0.09
    abant
    0.09
    Activations Density 0.064%

    No Known Activations