© 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. 60413
    Prev
    Next
    INDEX
    Explanations

    brightness and faintness of stars

    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
    ARGV
    -0.07
     lean
    -0.07
     напÑĢа
    -0.06
    èŀºæĿĨ
    -0.06
    /general
    -0.06
    èµ°åIJijäºĨ
    -0.06
    openh
    -0.06
     Lean
    -0.06
    导åIJij
    -0.06
    zerw
    -0.06
    POSITIVE LOGITS
    亮度
    0.09
     brightness
    0.09
     emitted
    0.08
    åıijåĩºçļĦ
    0.08
     faint
    0.08
     brighter
    0.08
     brightest
    0.08
    åħīæºIJ
    0.08
    微弱
    0.08
     occult
    0.08
    Activations Density 0.015%

    No Known Activations