© 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. 51552
    Prev
    Next
    INDEX
    Explanations

    entry date or court cases

    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
    åĬ©äºº
    -0.07
    ä¸Ģä¸ĭ
    -0.07
    Ù°
    -0.07
    eben
    -0.06
    QtCore
    -0.06
    èĭ±è¯ŃåĽĽçº§
    -0.06
    antal
    -0.06
    uz
    -0.06
    Äħtek
    -0.06
    isque
    -0.06
    POSITIVE LOGITS
    ëĤĺë§Ī
    0.08
    νοÏį
    0.07
    erer
    0.07
    bach
    0.07
    ëĿ¼ëıĦ
    0.07
    ope
    0.07
    olson
    0.06
    atria
    0.06
    ãģ¿ãģ®
    0.06
    awas
    0.06
    Activations Density 0.452%

    No Known Activations