© 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. 33816
    Prev
    Next
    INDEX
    Explanations

    court of appeals

    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
    lesa
    -0.08
    ero
    -0.06
    èķ
    -0.06
    eros
    -0.05
    æ¤Ĵ
    -0.05
     E
    -0.05
    åĬ¨éĿĻ
    -0.05
    éro
    -0.05
    iling
    -0.05
    iento
    -0.05
    POSITIVE LOGITS
    äºĮåŃĹ
    0.10
    Unchecked
    0.10
    verst
    0.08
    ülés
    0.08
    intree
    0.08
    finder
    0.08
    æĪij们ä¼ļ尽快
    0.08
    天æĪIJ
    0.08
     appunto
    0.08
    ä¸İæľ¬ç«Ļ
    0.08
    Activations Density 0.007%

    No Known Activations