© 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. 11993
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols in code

    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
    .nt
    -0.07
    ä¹İåħ¶
    -0.07
    idu
    -0.07
     jem
    -0.07
    Href
    -0.07
    aktır
    -0.07
    BarButton
    -0.07
    xcf
    -0.07
    ISIBLE
    -0.06
    interopRequire
    -0.06
    POSITIVE LOGITS
    å°±ä¸įè¦ģ
    0.07
    äºĭäºĨ
    0.07
     Loren
    0.07
     amat
    0.06
    yk
    0.06
    zeni
    0.06
    edis
    0.06
    飶
    0.06
     Barnett
    0.06
    é¡»çŁ¥
    0.06
    Activations Density 0.026%

    No Known Activations