© 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. 5616
    Prev
    Next
    INDEX
    Explanations

    as

    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»ĸ们
    -0.10
    å°ıå¿ĥ
    -0.10
    [OF
    -0.09
    èµ·èįī
    -0.09
    ä¸įçIJĨ
    -0.09
    èĵĵ
    -0.09
    åħħåĪĨåıijæĮ¥
    -0.09
    лин
    -0.09
    é¢ĸ
    -0.08
    éĢĢå¸Ĥ
    -0.08
    POSITIVE LOGITS
    ä½ľä¸º
    0.37
    ä½ľçĤº
    0.30
    ä½ľä¸ºä¸Ģ个
    0.29
    ä½ľä¸ºä¸Ģç§į
    0.29
    å½ĵä½ľ
    0.27
     sebagai
    0.25
    å½ĵåģļ
    0.24
     jako
    0.22
     as
    0.22
    ä½ľä¸ºä¸ĢåIJį
    0.22
    Activations Density 0.439%

    No Known Activations