© 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. 19808
    Prev
    Next
    INDEX
    Explanations

    fits well

    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
    åĬªåĬĽ
    -0.10
    æ±Ŀ
    -0.09
    .CG
    -0.09
    Selectable
    -0.08
    æľīä»·åĢ¼çļĦ
    -0.08
    å¯Ł
    -0.08
    ime
    -0.08
    mere
    -0.08
    é»İæĺİ
    -0.08
    è´Ń票
    -0.08
    POSITIVE LOGITS
    éĿŀ常éĢĤåIJĪ
    0.19
    æľĢéĢĤåIJĪ
    0.19
    æľĢåIJĪéĢĤ
    0.18
    æĽ´éĢĤåIJĪ
    0.17
    éĢĤåIJĪ
    0.15
    åĪļ好
    0.15
    ä¸įéĢĤåIJĪ
    0.15
     suited
    0.14
    åIJĪéĢĤ
    0.14
    æŃ£å¥½
    0.14
    Activations Density 0.074%

    No Known Activations