© 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. 33904
    Prev
    Next
    INDEX
    Explanations

    your, you, yours

    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
    对ä¸įèµ·
    -0.10
    æģ¶éŃĶ
    -0.09
    Ĥæķ°
    -0.09
    æ´İ
    -0.09
    æľĢå¿«
    -0.09
    ðŁĴ¯
    -0.09
    æĺŁçIJĥ
    -0.08
    åı»
    -0.08
    æŁłæª¬
    -0.08
    æĻĵå¾Ĺ
    -0.08
    POSITIVE LOGITS
    å¯¹ä½ł
    0.18
     your
    0.18
    your
    0.16
    ä½łçļĦ
    0.16
    æĤ¨çļĦ
    0.16
     YOUR
    0.15
    æĺ¯ä½ł
    0.15
     ваÑĪего
    0.15
    æĤ¨çļĦåŃ©åŃIJ
    0.14
    éĢĤåIJĪèĩªå·±
    0.14
    Activations Density 0.156%

    No Known Activations