© 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. 15130
    Prev
    Next
    INDEX
    Explanations

    anesthesia, fetus, per, cell, job, pleural, crew, in, between

    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
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.08
    acce
    -0.08
    è¿Ľè¡Įçİ°åľº
    -0.07
    ceau
    -0.07
    íĻĢ
    -0.07
    以任ä½ķ
    -0.07
    acci
    -0.07
    Ñĩей
    -0.07
    éķ¿æľŁä»İäºĭ
    -0.07
    æĮģç»ŃæıIJåįĩ
    -0.07
    POSITIVE LOGITS
    åĪ©æĸ¯
    0.07
    idia
    0.06
    å¤Ł
    0.06
    æ·³
    0.06
     Spiegel
    0.06
     tzw
    0.06
     Mellon
    0.06
     Medicaid
    0.06
     herk
    0.06
    åī¯äº§åĵģ
    0.06
    Activations Density 0.391%

    No Known Activations