© 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. 31470
    Prev
    Next
    INDEX
    Explanations

    time and scheduling

    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
    å¿Ļ
    -0.18
    å¿Ļç¢Į
    -0.17
    ç¹ģå¿Ļ
    -0.15
    å¿ĻçĿĢ
    -0.13
     Busy
    -0.12
    ç²¾åĬĽ
    -0.12
    ä¸ĬçıŃ
    -0.12
    Busy
    -0.12
     busy
    -0.11
    åĢ¦
    -0.11
    POSITIVE LOGITS
    วา
    0.10
    æĢĽ
    0.10
    è¾ĥ强çļĦ
    0.09
    ACLE
    0.09
    ÙħÙĤاÙĦات
    0.09
    serialize
    0.09
    æĤ¼
    0.08
     scouting
    0.08
    .ls
    0.08
    ç®Ń
    0.08
    Activations Density 0.055%

    No Known Activations