© 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. 9824
    Prev
    Next
    INDEX
    Explanations

    fire or gin

    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
    alais
    -0.09
    allis
    -0.08
    igel
    -0.07
    بط
    -0.07
    åĴĮçī¹çĤ¹
    -0.07
    angat
    -0.07
     ARISING
    -0.07
     brisk
    -0.07
    é¦ĸ
    -0.07
    è´§åĪ°
    -0.06
    POSITIVE LOGITS
     metaphor
    0.07
    éļIJåĸ»
    0.07
    象å¾ģçĿĢ
    0.07
    æĺ¯ä»Ģä¹ĪæĦıæĢĿ
    0.07
     invention
    0.07
    ẫn
    0.06
    象å¾ģ
    0.06
     metaph
    0.06
    象徵
    0.06
    yk
    0.06
    Activations Density 0.494%

    No Known Activations