© 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. 1421
    Prev
    Next
    INDEX
    Explanations

    features / insurance / Ridge / occasional

    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
    åı¤å±ĭ
    -0.08
    ouv
    -0.08
    èĢĮä¸ĭ
    -0.08
    åĤ¢
    -0.07
    untr
    -0.07
    gra
    -0.07
    ÙĥÙĨ
    -0.07
    èĢĮéĻį
    -0.07
    ubern
    -0.07
    æĢĿãģĦ
    -0.07
    POSITIVE LOGITS
    ä¸Ĭè¿°
    0.09
    åľ¨ä¸Ĭè¿°
    0.08
    å¼Ģ头çļĦ
    0.08
    ?,?,?,?,
    0.07
    inch
    0.07
    ä¸Ĭè¿°äºĭå®ŀ
    0.07
    eny
    0.07
    ock
    0.07
    åīįè¿°
    0.07
     etc
    0.07
    Activations Density 0.037%

    No Known Activations