© 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. 16488
    Prev
    Next
    INDEX
    Explanations

    legal citations and numbers

    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
     напÑĢа
    -0.07
    edic
    -0.07
    ðŁ
    -0.07
    èĢĮéĻį
    -0.07
    èĭ¥å¹²ä¸ª
    -0.06
    otype
    -0.06
    ãģ¾ãģĹãģ¦
    -0.06
     revan
    -0.06
     dip
    -0.06
     [...]
    -0.06
    POSITIVE LOGITS
    åIJĮä¸Ĭ
    0.07
    uschen
    0.07
     endorsed
    0.07
    (boost
    0.07
     Ibid
    0.07
    quet
    0.07
    åľ¨è¿Ľåħ¥
    0.07
    å¾Ĺ天
    0.06
    åĽ½åºĨ
    0.06
     endorsements
    0.06
    Activations Density 0.021%

    No Known Activations