© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9741
    Prev
    Next
    INDEX
    Explanations

    dating sites and tips

    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
    éļıæīĭ
    -0.09
    ç¿Ķ
    -0.09
     Dane
    -0.09
    æĭ¾
    -0.09
    è¹Ī
    -0.09
    æģĥ
    -0.08
    大桥
    -0.08
    骰
    -0.08
    è´¢æĬ¥
    -0.08
    ç»Ŀ大éĥ¨åĪĨ
    -0.08
    POSITIVE LOGITS
    åľºä¸Ĭ
    0.10
    plate
    0.09
    ysis
    0.08
    纷纷
    0.08
    åŃIJå¼Ł
    0.08
    ability
    0.08
    pling
    0.08
    æľ¦èĥ§
    0.08
    åľºéĿ¢
    0.08
    ToDevice
    0.08
    Activations Density 0.018%

    No Known Activations