© 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. 29916
    Prev
    Next
    INDEX
    Explanations

    Sullivan, dates, professionals

    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
    ä¹Įé²ģ
    -0.08
    åı«ä½ł
    -0.08
    HTTPRequest
    -0.08
    æľĢæĸ°æĸĩç«ł
    -0.08
    好æĸĩ
    -0.07
    kurat
    -0.07
    ä¸įçŁ¥æīĢ
    -0.07
    Ukra
    -0.07
    opor
    -0.07
    adow
    -0.07
    POSITIVE LOGITS
    oom
    0.06
    oft
    0.06
    ief
    0.06
    é¦ģ
    0.06
    ior
    0.06
    ç»ĺ
    0.06
    umin
    0.06
    寻
    0.06
     Davide
    0.06
    ä¹ĺ
    0.06
    Activations Density 0.705%

    No Known Activations