© 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. 38228
    Prev
    Next
    INDEX
    Explanations

    first

    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
    å±ħå¤ļ
    -0.07
     Sih
    -0.07
     autant
    -0.07
     sortes
    -0.07
    errs
    -0.07
    'autres
    -0.07
    pyx
    -0.06
    ä¸ĢæŶ
    -0.06
    çĻ¾æĪĺ
    -0.06
    á»ģu
    -0.06
    POSITIVE LOGITS
     überhaupt
    0.12
    ä¹Łæĺ¯æľĢ
    0.12
    åĴĮæľĢ
    0.11
     ooit
    0.10
     ever
    0.10
    åĴĮ第äºĮ
    0.10
    -ever
    0.10
     EVER
    0.09
     encountered
    0.08
    Ever
    0.08
    Activations Density 0.203%

    No Known Activations