© 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. 19381
    Prev
    Next
    INDEX
    Explanations

    too much or too many

    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
     ниÑĩ
    -0.09
    plib
    -0.09
    .hu
    -0.09
    appable
    -0.08
    ä¸įåĪĨ
    -0.08
    VERY
    -0.08
     жел
    -0.08
    ibus
    -0.08
    çīĴ
    -0.08
    é«ĺæ½®
    -0.08
    POSITIVE LOGITS
    太å¤ļ
    0.12
    å®ŀåľ¨å¤ª
    0.12
    太å¤ļäºĨ
    0.12
    太大
    0.12
    太å°ij
    0.11
    æ¯ķç«Ł
    0.11
    太å¤ļçļĦ
    0.11
    积累
    0.10
    çķ¢ç«Ł
    0.10
    linger
    0.09
    Activations Density 0.034%

    No Known Activations