© 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. 50416
    Prev
    Next
    INDEX
    Explanations

    č followed by code elements

    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
    asca
    -0.08
    ennai
    -0.08
    oport
    -0.07
    pati
    -0.07
    idot
    -0.07
    åĶł
    -0.07
    ạp
    -0.07
    opsis
    -0.07
    cipt
    -0.07
    apor
    -0.07
    POSITIVE LOGITS
    udd
    0.07
    udden
    0.06
     ÙħØŃ
    0.06
    æľīåı²
    0.06
     nowhere
    0.06
    е
    0.06
    ebra
    0.06
    çĶ¨å·¥
    0.06
    .contract
    0.06
    ç²¾å¿ĥç»Ħç»ĩ
    0.06
    Activations Density 0.744%

    No Known Activations