© 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. 27530
    Prev
    Next
    INDEX
    Explanations

    function F:V, kron(A,B), xf(y)+f(f(y))<=f(x+y), BinTree a -> BinTree a

    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
    ä¸ĵ家çļĦ
    -0.08
    ä¸ĵ家åĴĮ
    -0.08
    å°Ī家
    -0.07
    ä¸ĵ家认为
    -0.07
    æī¾åĽŀ
    -0.07
    allen
    -0.06
    ä¸ĵ家è¯Ħ审
    -0.06
    rees
    -0.06
    доз
    -0.06
    ewan
    -0.06
    POSITIVE LOGITS
    ç¡Ģ
    0.08
     mover
    0.07
    aley
    0.07
    åѦå¾Ĵ
    0.07
    pter
    0.07
    ä¹ħ
    0.07
    _added
    0.07
    æ°´äºķ
    0.07
    .getElementsByClassName
    0.06
    .sym
    0.06
    Activations Density 0.002%

    No Known Activations