© 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. 28427
    Prev
    Next
    INDEX
    Explanations

    trivial

    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
    ãģŁãģ£ãģŁ
    -0.08
    赫çĦ¶
    -0.08
    пев
    -0.07
     exclusively
    -0.06
    lev
    -0.06
    UED
    -0.06
    łíĮ
    -0.06
    ourage
    -0.06
    haled
    -0.06
    ivet
    -0.06
    POSITIVE LOGITS
    erweise
    0.10
    mente
    0.08
     truths
    0.08
    ä¸įæĺ¯åIJĹ
    0.08
    ly
    0.08
     nhiên
    0.08
    istically
    0.08
     módon
    0.08
    ously
    0.08
    èĪ¬åľ°
    0.08
    Activations Density 0.004%

    No Known Activations