© 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. 32187
    Prev
    Next
    INDEX
    Explanations

    levels of measures

    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
    ä»ħæıIJä¾Ľ
    -0.07
    _verbose
    -0.07
    ëŁ
    -0.06
    çĥģ
    -0.06
    ukan
    -0.06
    ovac
    -0.06
    .wik
    -0.06
    evol
    -0.06
    æľīä¸Ģé¢Ĺ
    -0.06
     removeFrom
    -0.06
    POSITIVE LOGITS
    æŁIJäºĽ
    0.16
     certain
    0.14
     various
    0.13
    åIJĦç§į
    0.13
     berbagai
    0.12
    åIJĦ项
    0.12
     ê°ģì¢ħ
    0.12
    çļĦåIJĦ项
    0.11
     Certain
    0.11
    åIJĦéłħ
    0.11
    Activations Density 0.815%

    No Known Activations