© 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. 9776
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
    æľī大éĩıçļĦ
    -0.10
    illions
    -0.09
    ä¸Ģ大
    -0.09
    å°ij许
    -0.09
    irim
    -0.08
    èŁĴ
    -0.08
    æĺ¯ä¸Ģä½į
    -0.08
    _requires
    -0.08
     countless
    -0.08
    çĤ¹å¤ļ
    -0.08
    POSITIVE LOGITS
    åĽ´ç»ķ
    0.09
    ãģ¤ãģ®
    0.09
    å®īæĬļ
    0.08
    بدÙĦ
    0.08
    iale
    0.08
    jin
    0.08
    鸥
    0.08
    èİİ
    0.08
    符åIJĪæĿ¡ä»¶
    0.08
    éĴ¡
    0.08
    Activations Density 0.370%

    No Known Activations