© 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. 1726
    Prev
    Next
    INDEX
    Explanations

    lines parallel to

    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
    é¼ĵ
    -0.06
     Stor
    -0.06
    æł¸å¿ĥ
    -0.06
     Sach
    -0.06
    meric
    -0.06
    饱满
    -0.06
    oken
    -0.06
     core
    -0.06
     migration
    -0.06
    æ¤Ĵ
    -0.06
    POSITIVE LOGITS
    araf
    0.09
     tangent
    0.08
    jeta
    0.08
    ÑĤикÑĥ
    0.08
    kini
    0.08
    aze
    0.08
    uÃŁ
    0.08
    rror
    0.08
    à¸Ĺิศ
    0.08
    éĩijåĪ©
    0.08
    Activations Density 0.003%

    No Known Activations