© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15042
    Prev
    Next
    INDEX
    Explanations

    light-activated processes

    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
    æĸ°åĬłåĿ¡
    -0.09
    á»ĩm
    -0.07
    èIJ¦
    -0.07
    jú
    -0.07
    -sided
    -0.07
    ä½ĵçİ°
    -0.07
    ÙĨب
    -0.07
    æŀģçĤ¹
    -0.07
     mach
    -0.07
    (/^\
    -0.07
    POSITIVE LOGITS
    çħ§å°Ħ
    0.13
     sunlight
    0.11
     irradi
    0.10
    åħīçħ§
    0.10
     photons
    0.10
    缴å°Ħ
    0.10
    åħīçļĦ
    0.10
    æĹ¥åħī
    0.10
    phot
    0.09
     exposure
    0.09
    Activations Density 0.083%

    No Known Activations