© 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. 46263
    Prev
    Next
    INDEX
    Explanations

    up in, conditioner in

    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
    utin
    -0.08
    rige
    -0.07
    æĿ¨æŁ³
    -0.07
     (...)
    -0.07
     [...]
    -0.07
    èĩ³æѤ
    -0.06
    ukt
    -0.06
    ä¸ĢæľĽ
    -0.06
    _variant
    -0.06
    ần
    -0.06
    POSITIVE LOGITS
    ocol
    0.08
    arrass
    0.08
    indre
    0.07
    oppi
    0.07
    erin
    0.07
    ãģĵãģ¡ãĤī
    0.07
    kp
    0.07
    esting
    0.07
    áĢ·áĢº
    0.07
    uala
    0.07
    Activations Density 0.258%

    No Known Activations