© 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. 62386
    Prev
    Next
    INDEX
    Explanations

    real-time and timely

    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
    åŀ«
    -0.09
    éļıå¤Ħ
    -0.09
    她说
    -0.09
    ä¼ĺæĥł
    -0.09
    æݨ
    -0.09
    ä¸įçĶ¨
    -0.08
    TT
    -0.08
    红线
    -0.08
    åķı
    -0.08
    æįŁå®³
    -0.07
    POSITIVE LOGITS
     timely
    0.15
     ká»ĭp
    0.13
    åıĬæŶ
    0.13
    æŶéĹ´åĨħ
    0.13
    éĢĤæŶ
    0.11
    æĮīæŶ
    0.11
    å¤Ł
    0.11
    å®ŀæŶ
    0.10
     اÙĦÙĪÙĤت
    0.10
    æĶ¶åĽŀ
    0.10
    Activations Density 0.027%

    No Known Activations