© 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. 22536
    Prev
    Next
    INDEX
    Explanations

    timing and sequence

    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
    æģ°æģ°
    -0.10
    æ¯ĶæĪij
    -0.09
    ä¹ı
    -0.09
    odes
    -0.08
    åģıåģı
    -0.08
    èĢĮåIJİ
    -0.08
    åļ
    -0.08
    æıIJé«ĺäºĨ
    -0.08
    é¦ĸä½į
    -0.08
    éĹ°
    -0.08
    POSITIVE LOGITS
    æľīä¸Ģå®ļçļĦ
    0.10
    ehr
    0.10
     fuzz
    0.09
    æIJ¬è¿IJ
    0.09
     conspir
    0.09
    æĦı大
    0.09
    chandle
    0.09
    黥
    0.09
    åģ·
    0.09
    å¸Ļ
    0.09
    Activations Density 0.030%

    No Known Activations