© 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. 5316
    Prev
    Next
    INDEX
    Explanations

    units or collections

    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
    æµ·éĩı
    -0.09
    诡
    -0.09
    ä½ĵ
    -0.09
    æ¾¹
    -0.09
    ASY
    -0.09
    ipers
    -0.09
    åģ¥åħ¨
    -0.09
    ç½ħ
    -0.09
    仪
    -0.08
    丰å¯Į
    -0.08
    POSITIVE LOGITS
    群
    0.09
    ä¸ĢçĤ¹ä¹Łä¸į
    0.09
    æĪĸå¤ļ
    0.09
    rema
    0.09
    jes
    0.08
    åĮĸè¿Ľç¨ĭ
    0.08
    oles
    0.08
    é«ĺä½İ
    0.08
    åĩĨ
    0.08
     báºŃt
    0.08
    Activations Density 0.124%

    No Known Activations