© 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. 39157
    Prev
    Next
    INDEX
    Explanations

    electrophoresis, chromatography, phase

    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
    canf
    -0.08
     notar
    -0.07
    æ±ĤçĶŁåŃĺ
    -0.07
    åĿłèIJ½
    -0.07
    ersh
    -0.07
     salv
    -0.07
    åıijçĶµéĩı
    -0.07
    èī¯åĵģ
    -0.07
    çŀ©
    -0.06
    èĢĢçľ¼çļĦ
    -0.06
    POSITIVE LOGITS
    esis
    0.08
    æĢ¯
    0.08
    -webpack
    0.07
    breadcrumb
    0.07
    æłĹ
    0.07
    è¿ĶåĽŀ顶éĥ¨
    0.07
    èĬ±é¦Ļ
    0.07
    euw
    0.07
    arrera
    0.07
     Emerald
    0.07
    Activations Density 0.043%

    No Known Activations