© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58884
    Prev
    Next
    INDEX
    Explanations

    locations, organizations, or points in time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    éĹ®é¢ĺæŶ
    -0.10
    æĻĤãģ«ãģ¯
    -0.08
    .setOn
    -0.08
    å·¥ä½ľæŶ
    -0.08
    æĿ¥çļĦæŶåĢĻ
    -0.08
    ä»ĬåĽŀãģ¯
    -0.08
    æŶè¦ģ
    -0.08
    å¾Īä¹ħäºĨ
    -0.08
    ä½ľä¸ļæŶ
    -0.08
    缮åīįæľī
    -0.07
    POSITIVE LOGITS
    表çݰ为
    0.09
    æĺ¾å¾Ĺæł¼å¤ĸ
    0.09
     still
    0.09
    å°±ä¸įåĨį
    0.08
    å°±åıĺæĪIJäºĨ
    0.08
     becomes
    0.08
     become
    0.08
    ä»į
    0.08
    ä»įæľª
    0.08
    ä»įçĦ¶
    0.08
    Activations Density 0.299%

    No Known Activations