© 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. 9771
    Prev
    Next
    INDEX
    Explanations

    place names and origins

    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
    antium
    -0.10
    åĹĵ
    -0.10
    å°ıäºĭ
    -0.10
    å¦Ĥæŀľä½łæĥ³
    -0.09
    rarian
    -0.09
    å¿Ĵ
    -0.09
    æĪijåıªæĺ¯
    -0.09
    ÑĥÑĩа
    -0.09
    éķ¿è¿ľ
    -0.09
    çī¹èī²çļĦ
    -0.09
    POSITIVE LOGITS
    ÙĬات
    0.09
    é¾Ļæ³ī
    0.09
    温æ³ī
    0.09
    å¦ĩ
    0.09
    åĪĩ
    0.08
    æĺ¥é£İ
    0.08
    æĴij
    0.08
    èĮĥ
    0.08
     expansions
    0.08
    ä¸įå®ļ
    0.08
    Activations Density 0.010%

    No Known Activations