© 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. 29885
    Prev
    Next
    INDEX
    Explanations

    specializing in or describing interests

    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
     constituted
    -0.06
    åĬ³åĬ¨
    -0.06
    ä¸İä»ĸ
    -0.06
    åĬ³
    -0.06
    ×Ļ׳×ķ
    -0.06
    ym
    -0.06
    åİ»åIJĥ
    -0.06
    جاÙĨ
    -0.06
    æħ§
    -0.06
    erry
    -0.06
    POSITIVE LOGITS
    å´Ĺ
    0.09
    主è¦ģä»İäºĭ
    0.08
    主ãģ«
    0.08
     gär
    0.08
    å¾ŀäºĭ
    0.08
    ä¸ĢèĪ¬é¡¹çĽ®
    0.08
     ì£¼ë¡ľ
    0.07
    quis
    0.07
     mainly
    0.07
    vari
    0.07
    Activations Density 1.048%

    No Known Activations