© 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. 25138
    Prev
    Next
    INDEX
    Explanations

    barber, candy, ISPR, everyone playing, qualities

    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
    ~
    -0.08
    Ñħо
    -0.07
     comparatively
    -0.07
    äºĮèĢħ
    -0.07
    æŃ£æĺ¯åľ¨
    -0.07
    åĪ°äºº
    -0.07
    åħ¸åŀĭ
    -0.07
    å¥ijåIJĪ
    -0.07
    æIJŀ好
    -0.07
    çİ°å®ŀ
    -0.06
    POSITIVE LOGITS
    éĻĦä¸Ĭä¸Ģ
    0.10
     \"
    0.09
    teis
    0.08
    _INLINE
    0.08
    .erb
    0.08
    (___
    0.08
    æĪijåĴĮæĪijçļĦ
    0.08
    åıijå±ķåĴĮæĶ¹éĿ©
    0.08
    请ç¨į
    0.07
    请åijĬçŁ¥
    0.07
    Activations Density 0.003%

    No Known Activations