© 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. 2179
    Prev
    Next
    INDEX
    Explanations

    fusion power or stellar structure

    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
    åij¨åħ¨
    -0.07
     Zad
    -0.07
    èĢ³çĽ®
    -0.07
    ak
    -0.07
     drug
    -0.07
    åħ·æľīçĭ¬ç«ĭ
    -0.07
    éĩij马
    -0.07
    åIJ¸æ¯Ĵ
    -0.07
    鸦
    -0.07
    boom
    -0.07
    POSITIVE LOGITS
     cosmic
    0.09
    æĢ»åı°
    0.09
    çļĦçĥŃ
    0.08
     helium
    0.08
     stellar
    0.08
    çĤ¹çģ«
    0.08
     Cosmic
    0.08
    дж
    0.08
    çĥŃçģ«
    0.08
    çĥŃçļĦ
    0.08
    Activations Density 0.002%

    No Known Activations