© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38463
    Prev
    Next
    INDEX
    Explanations

    one of

    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
    åĿIJèIJ½
    -0.09
    dek
    -0.09
    åĪĨåĪ«æĺ¯
    -0.09
    æĺ¯æľĢ好çļĦ
    -0.09
    女æľĭåıĭ
    -0.09
    为åĩĨ
    -0.09
    åħ³éĶ®æĺ¯
    -0.09
    åħĪæĺ¯
    -0.09
    oti
    -0.08
    æ£Ĥ
    -0.08
    POSITIVE LOGITS
    ä¸įéĶĻçļĦ
    0.09
    -sided
    0.09
    å¾Ī好çļĦ
    0.08
    个å¤ļ
    0.08
    ITHER
    0.08
    å®ŀå®ŀåľ¨åľ¨
    0.08
    人å±ħ
    0.08
    oded
    0.08
    ãĤ¯ãĥŃ
    0.08
    ãĥ¼ãĥĹ
    0.08
    Activations Density 0.029%

    No Known Activations