© 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. 45060
    Prev
    Next
    INDEX
    Explanations

    ATR Reflectance Spectroscopy

    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
    liste
    -0.08
    ä¸Ģ身
    -0.07
    _ATTRIB
    -0.07
    以客æĪ·
    -0.07
    igr
    -0.07
    andel
    -0.07
    人æĹł
    -0.07
     Entret
    -0.07
    andi
    -0.07
    è¹´
    -0.07
    POSITIVE LOGITS
    èĪŁ
    0.08
    çİ»çĴĥ
    0.08
    çļĦçİ»çĴĥ
    0.08
    avais
    0.07
     instrument
    0.07
    lange
    0.07
    仪åĻ¨çļĦ
    0.07
    åº
    0.07
    æľīæĦŁ
    0.07
    åĽºå®ļ
    0.07
    Activations Density 0.002%

    No Known Activations