© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 32491
    Prev
    Next
    INDEX
    Explanations

    's, is, are

    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
    让æ¶Īè´¹èĢħ
    -0.09
    è¿ĻæĿ¡
    -0.09
    ermann
    -0.09
    æĤ¬æµ®
    -0.09
    æĸĵ
    -0.09
    ä¸Ģ项
    -0.09
    opsy
    -0.09
    èĽŃ
    -0.09
    åįĹå±±
    -0.09
    ä¸Ńä¿Ħ
    -0.09
    POSITIVE LOGITS
    enne
    0.08
     Nobel
    0.08
    erves
    0.08
     Beit
    0.08
    undi
    0.08
     Beet
    0.08
    etz
    0.07
    æĿ¥åĽŀ
    0.07
    丰å¯Įå¤ļ彩
    0.07
    aker
    0.07
    Activations Density 0.094%

    No Known Activations