© 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. 48001
    Prev
    Next
    INDEX
    Explanations

    Copyright notices. License information

    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
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.11
    coledì
    -0.08
    bob
    -0.07
     seedu
    -0.07
    agram
    -0.07
    éľ²åĩºä¸Ģ
    -0.07
    обе
    -0.07
    ä¸Ģ缮
    -0.07
     "&#
    -0.07
    மிழ
    -0.07
    POSITIVE LOGITS
     kud
    0.07
     kaya
    0.07
    ubl
    0.07
    vall
    0.06
    æ²½
    0.06
    astia
    0.06
    æįį
    0.06
    åĬłå¼ºåŃ¦ä¹ł
    0.06
    ç¾ļ
    0.06
    äng
    0.06
    Activations Density 0.854%

    No Known Activations