© 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. 17467
    Prev
    Next
    INDEX
    Explanations

    http:// link prefixes

    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
    edImage
    -0.09
    edList
    -0.09
    inyin
    -0.08
    æĪIJç«ł
    -0.08
    embro
    -0.08
    ữa
    -0.08
    -caption
    -0.08
    pite
    -0.07
    yc
    -0.07
    ại
    -0.07
    POSITIVE LOGITS
    ï¸İ
    0.07
    åī
    0.07
    _PLACE
    0.06
    imba
    0.06
    ằn
    0.06
    oš
    0.06
    ijs
    0.06
    çī
    0.06
    ä¸ĢåĪ»
    0.06
    æĢİä¹Īçľĭ
    0.06
    Activations Density 0.011%

    No Known Activations