© 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. 23257
    Prev
    Next
    INDEX
    Explanations

    not followed by something

    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
    åİŁæĿIJæĸĻ
    -0.09
    laden
    -0.09
    éĿŀæ³ķ
    -0.09
    离ä¸įå¼Ģ
    -0.09
    åĩºè½¨
    -0.08
    uido
    -0.08
    ä¸ĵæłı
    -0.08
     indian
    -0.08
    -Mail
    -0.08
     Ä°l
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.14
    ä»»ä½ķå½¢å¼ı
    0.12
    æŃ£å¸¸çļĦ
    0.11
    ä»»ä½ķ
    0.10
    ede
    0.10
    ä»»ä½ķä¸Ģ个
    0.09
    DED
    0.09
    ä»»ä½ķ人
    0.09
    ä¸Ŀ毫
    0.09
    åºĶæľīçļĦ
    0.09
    Activations Density 0.065%

    No Known Activations