© 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. 64046
    Prev
    Next
    INDEX
    Explanations

    citations like [[@B1]]

    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
    串
    -0.07
     Ouver
    -0.07
    å¦ĤæѤçļĦ
    -0.07
    chand
    -0.07
    isible
    -0.07
    ä¸įä½ıçļĦ
    -0.07
     Komun
    -0.07
    æģŃ
    -0.06
    -machine
    -0.06
    大æĺİ
    -0.06
    POSITIVE LOGITS
    _JO
    0.07
    eware
    0.07
    jsc
    0.07
    Ñģени
    0.07
     fulfilled
    0.07
    æĽ¹
    0.07
    æĬĬå®ĥ们
    0.07
    avs
    0.06
    ercul
    0.06
    触
    0.06
    Activations Density 0.008%

    No Known Activations