© 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. 33675
    Prev
    Next
    INDEX
    Explanations

    year or week

    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
    æ·ŀ
    -0.10
    æ¯ıå¹´
    -0.09
    æ¡Įä¸Ĭ
    -0.09
    å¿ĥ头
    -0.09
    秩
    -0.09
    身ä¸Ĭ
    -0.08
    ä¸ĸ人
    -0.08
    åĤ²
    -0.08
    ä¸Ģéĥ¨åĪĨ
    -0.08
    ä½İ温
    -0.08
    POSITIVE LOGITS
    кан
    0.09
    为æ°ij
    0.09
    æİ®
    0.08
    è¿Ļ两ç§į
    0.08
     CRE
    0.08
     traced
    0.08
    ãĥ¡ãĥ³ãĥĪ
    0.08
    åįİ侨
    0.07
    alom
    0.07
    å¸ĺ
    0.07
    Activations Density 0.022%

    No Known Activations