© 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. 45451
    Prev
    Next
    INDEX
    Explanations

    volume, number, or date

    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
    åĶı
    -0.08
    ä¿ł
    -0.08
    алан
    -0.08
    _COD
    -0.07
    यà¥ĭ
    -0.07
    /month
    -0.07
    å¸Īé£İ
    -0.07
    yth
    -0.07
    èľĵ
    -0.07
    AndView
    -0.07
    POSITIVE LOGITS
    ä¸ĢæľĽ
    0.07
    ÑĤÑı
    0.07
     geld
    0.06
     Acad
    0.06
    èĻļæĭŁåĮĸ
    0.06
     hang
    0.06
    宦
    0.06
    éĻĦ
    0.06
    elts
    0.06
    ä¸įè¡Į
    0.06
    Activations Density 0.024%

    No Known Activations