© 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. 12266
    Prev
    Next
    INDEX
    Explanations

    case where it

    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
    çĽĸ
    -0.08
    èĵĭ
    -0.07
     íĮIJ
    -0.07
    ове
    -0.07
    openh
    -0.07
    çļĦéĩįè¦ģä¾Ŀæį®
    -0.06
    念
    -0.06
    пÑĤи
    -0.06
    elled
    -0.06
    ÉĻrÉĻ
    -0.06
    POSITIVE LOGITS
    ä¸ŃåĽ½å®¶
    0.07
    ØŃاÙħ
    0.07
    å½ĵåħ¶
    0.07
     mila
    0.06
    stad
    0.06
    ä¸Ģèµ°
    0.06
    å½ĵä»ĸ们
    0.06
    holm
    0.06
    tml
    0.06
    .configure
    0.06
    Activations Density 0.019%

    No Known Activations