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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20517
    Prev
    Next
    INDEX
    Explanations

    single occurrences or one instance

    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
    ä¸įè¿ľ
    -0.09
    .mas
    -0.09
    ä¸įåģļ
    -0.08
    linger
    -0.08
    ä¸Ģç³»åĪĹ
    -0.08
    åı¦ä¸ĢåįĬ
    -0.08
    ç§¦åĽ½
    -0.08
    æĩĭ
    -0.08
    æľīæĽ´å¤ļçļĦ
    -0.08
    åįİ缼
    -0.08
    POSITIVE LOGITS
    éĥ½æ²¡æľī
    0.10
     سÙĪÙī
    0.10
    æľ¬åľŁ
    0.10
    åĵªæĢķ
    0.09
    åĵªæĢķæĺ¯
    0.09
    éĿĸ
    0.09
    ensch
    0.09
    Except
    0.09
    ocre
    0.08
    éĥ½æĹłæ³ķ
    0.08
    Activations Density 0.053%

    No Known Activations