© 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. 51659
    Prev
    Next
    INDEX
    Explanations

    celebrity relationships and news

    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
    æĪijå¿ĥéĩĮ
    -0.11
    æĪijèĩªå·±
    -0.11
    对æĪijæĿ¥è¯´
    -0.11
    ä¹İ
    -0.11
    éĩĮéĿ¢æľī
    -0.10
    itus
    -0.09
    è¡Ķ
    -0.09
    æĪij没
    -0.09
    è¿Ļæĺ¯æĪij
    -0.09
    æ´ĩ
    -0.09
    POSITIVE LOGITS
    æį®æĤī
    0.11
    ç½ijåıĭ们
    0.10
    ç½ijåıĭ
    0.09
    å¤ĸçķĮ
    0.09
    女æĺŁ
    0.09
    æĬ¥éģĵ称
    0.08
     claims
    0.08
     fans
    0.08
    æĽĿ
    0.08
    ä¸Ģç¬Ķ
    0.08
    Activations Density 0.344%

    No Known Activations