© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 47200
    Prev
    Next
    INDEX
    Explanations

    forecasts and estimates

    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
    Not in Any Lists

    No Comments

    Negative Logits
    falls
    -0.07
    æ·±åħ¥åŃ¦ä¹łè´¯å½»
    -0.07
    аÑĤо
    -0.07
    ÏĢοÏĦε
    -0.07
     jag
    -0.07
    æĬĺ弯
    -0.07
    èıģ
    -0.07
    å¾Ģåīįèµ°
    -0.07
    æīĢå±ŀåĪĨç±»
    -0.07
    _Thread
    -0.06
    POSITIVE LOGITS
    å½ĵæŶçļĦ
    0.10
    å½ĵæŶ
    0.10
    æ¯ı次éĥ½
    0.09
    ä¸Ĭä¸Ģ次
    0.08
    å½ĵ天çļĦ
    0.08
    æľ¬æ¬¡
    0.07
    å½ĵ天
    0.07
    èĢĮæѤæŶ
    0.07
     freshly
    0.07
     Bes
    0.07
    Activations Density 0.018%

    No Known Activations