© 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. 33503
    Prev
    Next
    INDEX
    Explanations

    Grand Prix

    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
    ike
    -0.06
    欣
    -0.06
    è§ģ
    -0.06
    اÙĨ
    -0.06
    Ģ
    -0.06
    è¿Ļä¸ĢçĤ¹
    -0.06
    lar
    -0.06
    iket
    -0.06
    RT
    -0.06
    æįŁ
    -0.06
    POSITIVE LOGITS
    utilus
    0.08
    igno
    0.08
    getInstance
    0.07
    ilton
    0.07
    enges
    0.07
    ekali
    0.07
    urg
    0.07
    å¸Ī表
    0.07
    |[
    0.07
    emma
    0.07
    Activations Density 0.004%

    No Known Activations