© 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. 38790
    Prev
    Next
    INDEX
    Explanations

    standard error confidence interval

    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
    boli
    -0.08
     Bolt
    -0.08
     soundtrack
    -0.08
    bolt
    -0.07
    ãģ¡ãĤĩãģĨ
    -0.07
    nasi
    -0.07
     readme
    -0.07
    ource
    -0.07
    ivamente
    -0.07
    amburg
    -0.07
    POSITIVE LOGITS
    å¨ģå°Ķ
    0.07
    ắm
    0.07
    -adjust
    0.07
    计ç®ĹçļĦ
    0.07
    sig
    0.07
    ä¹ĺ
    0.07
    诸èijĽ
    0.07
    opo
    0.07
    ë¥
    0.07
    EMB
    0.07
    Activations Density 0.003%

    No Known Activations