© 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. 10849
    Prev
    Next
    INDEX
    Explanations

    clock or watch time

    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
    éĢ¸
    -0.11
    ç¦ģ
    -0.09
    è¹ĭ
    -0.09
    ç¼ĺ
    -0.09
    éĩįå¿ĥ
    -0.09
    èĬ
    -0.08
    åĬłå¤§
    -0.08
    代表
    -0.08
     pr
    -0.08
    åī²
    -0.08
    POSITIVE LOGITS
    éĴŁ
    0.19
     clock
    0.16
    clock
    0.15
    æīĭ表
    0.14
    Clock
    0.14
    .clock
    0.14
     Clock
    0.14
     clocks
    0.14
    _clock
    0.14
    éIJĺ
    0.13
    Activations Density 0.124%

    No Known Activations