© 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. 58689
    Prev
    Next
    INDEX
    Explanations

    try

    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
    fax
    -0.08
    å¤įåĪ¶éĵ¾æİ¥
    -0.07
    ksi
    -0.07
    åIJİèĢħ
    -0.07
    åĨį继ç»Ń
    -0.07
     enfin
    -0.07
    رار
    -0.06
    ç½ļ
    -0.06
    rac
    -0.06
    /address
    -0.06
    POSITIVE LOGITS
    uth
    0.08
    åĢĴ
    0.07
    iente
    0.07
    ossa
    0.07
    ientes
    0.07
    æĬ±
    0.07
    unders
    0.07
    try
    0.07
    æıIJ
    0.06
    à®±à¯įà®±à¯ģ
    0.06
    Activations Density 0.201%

    No Known Activations