© 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. 51766
    Prev
    Next
    INDEX
    Explanations

    solid state crystallography

    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
    åı£å¾Ħ
    -0.09
    gut
    -0.09
    æ¼ıæĸĹ
    -0.09
    èĥĨæ±ģ
    -0.08
    út
    -0.08
    æµģéĩıçļĦ
    -0.08
    Ellipse
    -0.08
    òi
    -0.08
    amaha
    -0.08
    æĩ¸
    -0.08
    POSITIVE LOGITS
     crystal
    0.10
    æĻ¶
    0.10
     structure
    0.09
    æĻ¶ä½ĵ
    0.09
    ç»ĵæŀĦ
    0.09
     crystall
    0.09
     crystals
    0.09
     Structure
    0.08
    ç»ĵæĻ¶
    0.08
    建æĪIJ
    0.08
    Activations Density 0.043%

    No Known Activations