© 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. 3060
    Prev
    Next
    INDEX
    Explanations

    tips

    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
    æŶ任
    -0.08
    å°ģæݧ
    -0.07
    èĢģæľĭåıĭ
    -0.07
    æĪ¿åľ°
    -0.07
    æĸ°ä¹¦æݨèįIJ
    -0.07
    upa
    -0.07
    raf
    -0.06
    æĸĩæĹħ
    -0.06
    åıªåIJ¬
    -0.06
    unno
    -0.06
    POSITIVE LOGITS
     online
    0.08
    [url
    0.08
    åľ¨çº¿
    0.08
    èĮĥçķ´
    0.08
    (http
    0.08
    azol
    0.07
    adis
    0.07
    åľ¨çº¿åĴ¨è¯¢
    0.07
    ä¸įèĥ½å¤Ł
    0.07
    online
    0.07
    Activations Density 1.055%

    No Known Activations