© 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. 51065
    Prev
    Next
    INDEX
    Explanations

    how to

    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
    æIJģ
    -0.08
    ä¸įèĪį
    -0.07
    æĮijæĪĺ
    -0.07
     Ðķго
    -0.07
    isque
    -0.07
    å®Ī
    -0.07
    éķ¿éķ¿
    -0.07
    ками
    -0.07
    (Note
    -0.07
    ech
    -0.07
    POSITIVE LOGITS
    碲
    0.10
    ä¸Ģ个好çļĦ
    0.10
    é¢ĵ
    0.10
    astics
    0.09
    éĽķ
    0.09
    åºĶ该å¦Ĥä½ķ
    0.09
    æĦŁ
    0.09
    屯
    0.09
    æĪijå¸ĮæľĽ
    0.09
    scanner
    0.09
    Activations Density 0.449%

    No Known Activations