© 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. 50987
    Prev
    Next
    INDEX
    Explanations

    applause and positive reactions

    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
    å¤Ļ
    -0.09
    ettel
    -0.08
    éĶĭ
    -0.08
    TouchEvent
    -0.08
    gp
    -0.08
    éĿ¢è²Į
    -0.08
    panion
    -0.08
    ä¹ĭ家
    -0.08
    æµĵ
    -0.08
    ythe
    -0.08
    POSITIVE LOGITS
    åĴĮæĶ¯æĮģ
    0.13
    -worthy
    0.12
    å¸Ń
    0.09
    å¾Ĺèµ·
    0.09
    ä¹ĭä½ľ
    0.09
    家ä¼Ļ
    0.09
    èĨº
    0.09
    åĽ¢éķ¿
    0.09
    人å¿ĥ
    0.09
    åĪ°ä½į
    0.09
    Activations Density 0.006%

    No Known Activations