© 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. 21039
    Prev
    Next
    INDEX
    Explanations

    reporting, tutorials, ranked, stated

    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
    engen
    -0.08
    ä¸Ģéĩij
    -0.08
    plist
    -0.08
    itness
    -0.08
     unh
    -0.08
    estes
    -0.07
    ä»ħéĻIJ
    -0.07
     Abra
    -0.07
     \`
    -0.07
    chting
    -0.07
    POSITIVE LOGITS
     widely
    0.10
    éĢļå¸¸åľ¨
    0.09
     typically
    0.09
    éĢļ常
    0.09
     commonly
    0.08
     often
    0.08
    typically
    0.08
     usually
    0.08
    åľ¨è®¸å¤ļ
    0.08
    常è§ģ
    0.08
    Activations Density 0.357%

    No Known Activations