© 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. 56597
    Prev
    Next
    INDEX
    Explanations

    people, individuals, or users

    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
    åıµ
    -0.10
    åı¯éĿłçļĦ
    -0.09
    è´¼
    -0.09
    è¿Ļ家ä¼Ļ
    -0.09
    ä¸Ģæīĭ
    -0.08
    åı¯éĿł
    -0.08
    çľ¼çķĮ
    -0.08
    èĩ³å°ij
    -0.08
    ä¼ģä¸ļåľ¨
    -0.08
     ÙĦÙĥÙĦ
    -0.08
    POSITIVE LOGITS
     unsus
    0.10
    è´¬
    0.10
    åIJĪæ³ķæĿĥçĽĬ
    0.09
    å°Ĭ严
    0.09
    å¼±åĬ¿
    0.09
    (||
    0.09
    åīįæĿ¥
    0.09
    ubb
    0.09
    æĥ³è±¡
    0.08
    å¬
    0.08
    Activations Density 0.116%

    No Known Activations