© 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. 15218
    Prev
    Next
    INDEX
    Explanations

    PRINT statements or commands

    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
    ä¸Ģ举
    -0.09
    untura
    -0.08
    ä½Ĩä¹Łæľī
    -0.08
    ipur
    -0.08
    ois
    -0.08
    hend
    -0.08
    uida
    -0.08
    {_
    -0.08
    habit
    -0.08
    ajt
    -0.08
    POSITIVE LOGITS
    æļ
    0.07
     fa
    0.07
     sil
    0.06
    çŃīåħ¶ä»ĸ
    0.06
     Brooke
    0.06
    agi
    0.06
     ca
    0.06
    olk
    0.06
     Pi
    0.06
     Fa
    0.06
    Activations Density 0.018%

    No Known Activations