© 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. 24048
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and symbols

    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
    eba
    -0.08
    igger
    -0.07
    (QtCore
    -0.07
    ëĿ½
    -0.07
    origin
    -0.07
    owner
    -0.07
    Õ®
    -0.06
     rued
    -0.06
    ç¢
    -0.06
    kel
    -0.06
    POSITIVE LOGITS
    éĩijé¦Ļ
    0.07
    满éĿ¢
    0.07
    ussed
    0.07
    moil
    0.07
    æıĴä¸Ĭ
    0.07
    ä¸Ĭè¿°
    0.07
    è°¨
    0.07
    ottom
    0.07
    天å°Ĭ
    0.06
    áv
    0.06
    Activations Density 0.051%

    No Known Activations