© 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. 30350
    Prev
    Next
    INDEX
    Explanations

    units of time or duration

    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
    åĬ¬
    -0.09
    ä¸Ģç»ı
    -0.09
    鬣
    -0.09
    oti
    -0.08
    ány
    -0.08
    ç±³ç²ī
    -0.08
    ä½ĥ
    -0.08
    ä»¿ä½Ľ
    -0.08
    .Ma
    -0.08
    æĺİçĻ½
    -0.08
    POSITIVE LOGITS
    é«ĺä½İ
    0.09
    æĸ°äº§åĵģ
    0.09
    æĸ°åĵģ
    0.09
    DataContext
    0.08
    å±ł
    0.08
    DidLoad
    0.08
    åºŃ
    0.08
     kolej
    0.08
    elin
    0.08
    Borders
    0.08
    Activations Density 0.170%

    No Known Activations