© 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. 21519
    Prev
    Next
    INDEX
    Explanations

    news reporting Staff Report

    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
     fray
    -0.07
    éĩĩ
    -0.06
    ;charset
    -0.06
    ä¸į解
    -0.06
    wo
    -0.06
    å®ļæĢ§
    -0.06
    æŃ¢
    -0.06
    ewa
    -0.06
    erÃŃa
    -0.06
    è°ģèĥ½
    -0.06
    POSITIVE LOGITS
    odom
    0.08
    èĮĥæĸĩç½ij
    0.08
    dispatch
    0.07
    rette
    0.07
    Dispatch
    0.07
    TargetException
    0.07
    Installer
    0.07
     Lindsay
    0.07
    被她
    0.07
    çŀ³
    0.07
    Activations Density 0.166%

    No Known Activations