© 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. 31544
    Prev
    Next
    INDEX
    Explanations

    what is the

    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
    lint
    -0.09
    漫
    -0.09
    æ§İ
    -0.09
    åĩŃçĿĢ
    -0.09
    çĴľ
    -0.09
    æ³Ħ
    -0.09
    çijŁ
    -0.09
    天ä¸ĭ
    -0.08
    ç¥ŀå·ŀ
    -0.08
    æģ¢
    -0.08
    POSITIVE LOGITS
    æīĭåĬ¿
    0.09
     Spears
    0.09
    rist
    0.09
    çŃł
    0.09
    aic
    0.08
    åĢ®
    0.08
    uli
    0.08
    æĪijæĺ¯
    0.08
    åķ¼
    0.08
    ä¸Ģå®ļ
    0.08
    Activations Density 0.004%

    No Known Activations