© 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. 8065
    Prev
    Next
    INDEX
    Explanations

    techniques and methods

    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
    thing
    -0.09
    æĶ¾çŁ¢
    -0.08
    aby
    -0.08
    åĽ¾æºIJ
    -0.07
    templates
    -0.07
    owed
    -0.07
    λÏħ
    -0.07
    ÙĨدر
    -0.07
    izzi
    -0.07
    wich
    -0.07
    POSITIVE LOGITS
    ually
    0.10
    /method
    0.09
    uality
    0.09
    ipse
    0.09
    lify
    0.09
    eshire
    0.09
    åĴĮç»ıéªĮ
    0.08
    fully
    0.08
    çļĦè¿IJçĶ¨
    0.08
    iclet
    0.08
    Activations Density 0.022%

    No Known Activations