© 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. 60876
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with punctuation

    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
    ste
    -0.07
    ngen
    -0.06
    èĩªæĦ¿
    -0.06
    rais
    -0.06
    oj
    -0.06
    å¡ĺ
    -0.06
    uge
    -0.06
    orbit
    -0.06
    è§
    -0.06
     orbit
    -0.06
    POSITIVE LOGITS
    yss
    0.07
    yeur
    0.07
    ТС
    0.07
    åĪĽæĬķ
    0.07
    ProcessEvent
    0.07
    尼奥
    0.07
    åĪĨåĪ«ä¸İ
    0.07
    è¿Ŀåıįä¸Ĭè¿°
    0.07
    ovsky
    0.07
    é©®
    0.07
    Activations Density 0.010%

    No Known Activations