© 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. 58922
    Prev
    Next
    INDEX
    Explanations

    not followed by

    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
    åIJĮçŃī
    -0.11
     nevertheless
    -0.10
     каз
    -0.09
    ä¼ģä¸ļåĴĮ
    -0.09
    åıłåĬł
    -0.09
    没åħ³ç³»
    -0.09
    Sk
    -0.09
    为åĩĨ
    -0.08
    ç«ĭä½ĵ
    -0.08
    æ¯Ķäºļ
    -0.08
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.10
    èĢĮéĿŀ
    0.10
    æĸ¹åľĨ
    0.10
    rieve
    0.09
    çļĦä½ľåĵģ
    0.09
    éľģ
    0.09
    åģ¥åº·æĪIJéķ¿
    0.09
    诸
    0.08
    èĩ³äºİ
    0.08
    諸
    0.08
    Activations Density 0.028%

    No Known Activations