© 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. 16720
    Prev
    Next
    INDEX
    Explanations

    naturally occurring compounds

    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
    antics
    -0.08
    elang
    -0.08
    ä½ĻçĶŁ
    -0.08
     ÙĨÙģر
    -0.08
    æĸĩåĵ²
    -0.07
    ä¸ĵéĹ¨ä¸º
    -0.07
    angat
    -0.07
    çIJĨ论ä¸İå®ŀè·µ
    -0.07
    æķħä½ľ
    -0.07
    çIJĨ论åĴĮ
    -0.07
    POSITIVE LOGITS
    天çĦ¶
    0.15
     natural
    0.14
    èĩªçĦ¶
    0.13
    /original
    0.13
    çļĦèĩªçĦ¶
    0.13
    天çĦ¶çļĦ
    0.13
    /native
    0.13
    natural
    0.12
     naturally
    0.12
    èĩªçĦ¶çļĦ
    0.12
    Activations Density 0.145%

    No Known Activations