© 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. 17322
    Prev
    Next
    INDEX
    Explanations

    semiconductor injection holes electrons

    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
    ogr
    -0.09
    jak
    -0.08
    èĩªéĩį
    -0.07
    ç»ĨåĪĨ
    -0.06
    è§Ħéģ¿
    -0.06
    able
    -0.06
    é£İåIJij
    -0.06
    glieder
    -0.06
    ç¾ļ
    -0.06
     docking
    -0.06
    POSITIVE LOGITS
    æ®ī
    0.08
    cona
    0.08
    locals
    0.08
    èµĦæł¼å®¡æŁ¥
    0.08
     Kro
    0.08
     stray
    0.08
    committed
    0.07
    寿åij½
    0.07
    ç¦ģåĮº
    0.07
    大å¢ŀ
    0.07
    Activations Density 0.002%

    No Known Activations