© 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. 24482
    Prev
    Next
    INDEX
    Explanations

    daterange

    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
    aye
    -0.08
    éļıçĿĢå¹´é¾Ħ
    -0.08
    double
    -0.07
    éļı
    -0.06
    queur
    -0.06
    ambe
    -0.06
    _ob
    -0.06
    dbl
    -0.06
    èĢģäºĨ
    -0.06
    ä¸ĢçĶŁä¸Ń
    -0.06
    POSITIVE LOGITS
     inclusive
    0.12
    inclusive
    0.11
     inclus
    0.09
     contiguous
    0.09
     inclusiv
    0.09
    åĮħæĭ¬äºĨ
    0.08
     einschlieÃŁlich
    0.08
    æīĢè½½
    0.08
     inklus
    0.08
     encompass
    0.08
    Activations Density 0.008%

    No Known Activations