© 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. 24332
    Prev
    Next
    INDEX
    Explanations

    percentages or file extensions

    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
     arche
    -0.06
    ANEL
    -0.06
    .gs
    -0.06
    pragma
    -0.06
    xbf
    -0.06
    AREST
    -0.06
    anke
    -0.06
    ìĨIJ
    -0.06
    åıijçĶŁåIJİ
    -0.06
    å¼ıåĴĮ
    -0.06
    POSITIVE LOGITS
    èĦIJ
    0.08
    ä»¤ä½ł
    0.08
    ä¹Ŀå·ŀ
    0.07
     Trab
    0.07
    odzi
    0.07
    urrent
    0.07
    åįĥåŃĹ
    0.07
    游æĪıè§ĦåĪĻ
    0.07
    acity
    0.07
    âĢ¦"
    0.07
    Activations Density 0.040%

    No Known Activations