© 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. 4797
    Prev
    Next
    INDEX
    Explanations

    based on customer requirements

    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
    ä»»ä½ķéĹ®é¢ĺ
    -0.09
    çļĦéĹ®é¢ĺæĺ¯
    -0.09
    éĹ®é¢ĺæĺ¯
    -0.09
    åĨħ容åĮħæĭ¬
    -0.08
    çī¹å¾ģæĺ¯
    -0.08
    æĵįä½ľä¸Ĭ
    -0.08
    ä¼ļè®®çĶ±
    -0.08
    æĪIJåĪĨæĺ¯
    -0.08
    ä¼ĺçĤ¹æĺ¯
    -0.08
    使çĶ¨èµ·æĿ¥
    -0.08
    POSITIVE LOGITS
    æĥħåĨµæĿ¥çľĭ
    0.12
    å®ŀéĻħæĥħåĨµ
    0.11
    å·¥ä½ľå®ŀéĻħ
    0.10
    åıijå±ķçļĦéľĢè¦ģ
    0.09
    并ç»ĵåIJĪ
    0.09
    åı¯çŁ¥
    0.09
     principles
    0.08
    çļĦçī¹çĤ¹
    0.08
    çī¹çĤ¹
    0.08
    æĥħåĨµè¿Ľè¡Į
    0.08
    Activations Density 0.028%

    No Known Activations