© 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. 7608
    Prev
    Next
    INDEX
    Explanations

    funding for

    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
    骧
    -0.10
    åĬŁåĬ³
    -0.09
    èĬ±éĴ±
    -0.09
    .resp
    -0.09
    _MALLOC
    -0.09
    çĶµéĩı
    -0.09
    ria
    -0.08
    ../../../../
    -0.08
    çĥŃè¡Ģ
    -0.08
     Expert
    -0.08
    POSITIVE LOGITS
    ä¾
    0.09
    ç¼Ķ
    0.09
    licit
    0.09
    èĮ¨
    0.09
    æ·Ŀ
    0.09
    å¦Ĥå®ŀ
    0.08
    ç§ijåѦçłĶ究
    0.08
    iec
    0.08
    æĮº
    0.08
    符åIJĪæĿ¡ä»¶
    0.08
    Activations Density 0.062%

    No Known Activations