© 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. 4067
    Prev
    Next
    INDEX
    Explanations

    delimiters and symbols

    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
    elan
    -0.08
    inggu
    -0.07
    ç§ijæĬĢåѦéĻ¢
    -0.07
    isle
    -0.07
    fras
    -0.07
    èģĮä¸ļåѦéĻ¢
    -0.06
    atico
    -0.06
    .setAuto
    -0.06
    è¡Ĩ
    -0.06
    ä¹ħçļĦ
    -0.06
    POSITIVE LOGITS
    æĮĩ示
    0.08
    iple
    0.07
    IgnoreCase
    0.07
     presenti
    0.07
    èIJĿ
    0.07
    ialog
    0.07
    izzi
    0.07
     appos
    0.06
    æĮĩ示精ç¥ŀ
    0.06
     delim
    0.06
    Activations Density 0.020%

    No Known Activations