© 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. 4188
    Prev
    Next
    INDEX
    Explanations

    code syntax and punctuation

    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
    Readable
    -0.09
    icei
    -0.09
    _fds
    -0.08
    _GEN
    -0.08
    MainThread
    -0.08
    ¤íĹ
    -0.08
    zub
    -0.08
     RUNNING
    -0.08
    ç¼ĸè¾ijäºİ
    -0.08
    alba
    -0.08
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.08
    '
    0.06
    é¢ł
    0.06
     present
    0.06
    å°
    0.06
    该ä¼ģä¸ļ
    0.06
    евой
    0.05
    åľ¨å½ĵåľ°
    0.05
    ä¸İ该
    0.05
     due
    0.05
    Activations Density 0.156%

    No Known Activations