© 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. 57856
    Prev
    Next
    INDEX
    Explanations

    table headers and separators

    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
    oron
    -0.08
    ÑĽ
    -0.07
     meanwhile
    -0.07
     Alem
    -0.07
    å¥Ĺ
    -0.07
    æŶèĩ³
    -0.07
    argas
    -0.07
    arg
    -0.07
    boh
    -0.07
    俨
    -0.07
    POSITIVE LOGITS
    ä¸īä¸ĥ
    0.07
    èĸĦ
    0.06
    usters
    0.06
    thin
    0.06
    ells
    0.06
    adol
    0.06
    èĤļ
    0.06
     CIT
    0.06
     separating
    0.06
    Clone
    0.06
    Activations Density 0.107%

    No Known Activations