© 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. 27352
    Prev
    Next
    INDEX
    Explanations

    breaks

    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
    éĴĹ
    -0.11
     Kensington
    -0.10
    æģ¤
    -0.09
    TEE
    -0.09
    ä½Ĩä¹Ł
    -0.09
    æģ¶
    -0.08
    ä½łèĩªå·±
    -0.08
    icide
    -0.08
    .infinity
    -0.08
    饷
    -0.08
    POSITIVE LOGITS
    ä¸¤å¼ł
    0.11
    èĻŀ
    0.09
    æī¯
    0.09
    æģ£
    0.09
    é©»æĿij
    0.08
    æģĭæĥħ
    0.08
    æĸ¹æĸ¹éĿ¢
    0.08
    oram
    0.08
    è¿Ļå¼ł
    0.08
    é»ijé¾Ļ
    0.08
    Activations Density 0.004%

    No Known Activations