© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14738
    Prev
    Next
    INDEX
    Explanations

    numbers and fractions

    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
    edur
    -0.08
    ields
    -0.07
    CursorPosition
    -0.07
    çľĭå¾ĹåĩºæĿ¥
    -0.06
    .EntityFramework
    -0.06
    éĩĮåħĭ
    -0.06
    åŁ¹
    -0.06
    actory
    -0.06
    念
    -0.06
    /items
    -0.06
    POSITIVE LOGITS
    à¹Ģà¸Ľà¸¥à¹Īา
    0.07
     mandar
    0.07
    /*@
    0.07
    ιÏĥ
    0.07
    lal
    0.07
     Twe
    0.07
    tus
    0.07
     Ts
    0.07
    aghan
    0.07
    nett
    0.07
    Activations Density 0.004%

    No Known Activations