© 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. 16644
    Prev
    Next
    INDEX
    Explanations

    report by

    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
    å¸Ĥåľºè°ĥæŁ¥
    -0.08
    å¸Ĥåľºè°ĥçłĶ
    -0.07
    -dismiss
    -0.06
    ÏĢον
    -0.06
    åĪ°åºŃ
    -0.06
    edig
    -0.06
    æ¯Ķä¾ĭçļĦ
    -0.06
    رضا
    -0.06
    éĽ¨éľ²
    -0.06
    å¢ħ
    -0.06
    POSITIVE LOGITS
    ä¹Łå°±ä¸į
    0.10
    åıįèĢĮä¼ļ
    0.09
    å¾·æĸ¯
    0.08
    usher
    0.08
     ê·¸ë§Įíģ¼
    0.08
    çļĦäººä¹Ł
    0.07
     accordingly
    0.07
    åıįèĢĮ
    0.07
    ายุ
    0.07
    lei
    0.07
    Activations Density 0.002%

    No Known Activations