© 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. 34116
    Prev
    Next
    INDEX
    Explanations

    url prefixes

    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
    线ä¸ĬçļĦ
    -0.07
    stvo
    -0.07
    å½ĵä¸ŃçļĦ
    -0.07
    è¿
    -0.06
    ställ
    -0.06
    षà¥į
    -0.06
    å¤ļ空
    -0.06
    ä½ķæĸ¹
    -0.06
    Č
    -0.06
    å¾Ĺ以
    -0.06
    POSITIVE LOGITS
    emm
    0.09
    ebre
    0.08
    reso
    0.08
     Ansi
    0.08
    emps
    0.07
    uas
    0.07
    ä¸į说è¯Ŀ
    0.07
    rijk
    0.07
    rams
    0.07
    openh
    0.07
    Activations Density 0.007%

    No Known Activations