© 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. 11366
    Prev
    Next
    INDEX
    Explanations

    gifts and donations

    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
    rote
    -0.09
    éĴ§
    -0.09
    ä¸ĭæīĭ
    -0.09
    çļĦçľ¼çĿĽ
    -0.09
    èIJ¥åķĨçݯå¢ĥ
    -0.09
     wholesale
    -0.09
    æŃ£ä¹ī
    -0.08
    _approved
    -0.08
    _excerpt
    -0.08
    è¹Ģ
    -0.08
    POSITIVE LOGITS
    å®ŀçī©
    0.16
    礼çī©
    0.12
    ä»£æĽ¿
    0.10
    å¤ļç§įå½¢å¼ı
    0.09
    æĹłå½¢
    0.09
    è¿Ļç§įæĸ¹å¼ı
    0.09
    éĩijéĴ±
    0.09
    å¸ĤåĢ¼
    0.09
     gifts
    0.09
    人åĬĽ
    0.09
    Activations Density 0.072%

    No Known Activations