© 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. 42009
    Prev
    Next
    INDEX
    Explanations

    what is explained

    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
    TestFixture
    -0.09
    adesh
    -0.09
    pere
    -0.08
    å¹¼ç¨ļ
    -0.08
    LogFile
    -0.08
    ä¸ĩæĪ·
    -0.08
     prezi
    -0.08
    éħĹ
    -0.08
    immel
    -0.07
    åĭ¿æī°
    -0.07
    POSITIVE LOGITS
    ample
    0.08
    eat
    0.08
    x
    0.06
    ooth
    0.06
    ä¸įèĻļ
    0.06
    ç´«éĩij
    0.06
    æģĴ
    0.06
    eld
    0.06
    é»ĦèĬ±
    0.06
    eyed
    0.06
    Activations Density 0.001%

    No Known Activations