© 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. 32656
    Prev
    Next
    INDEX
    Explanations

    token group or ending

    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
    (...)
    -0.07
     bÃło
    -0.07
    âĢ¦
    -0.07
    gets
    -0.07
    好ä¸į
    -0.06
    ijing
    -0.06
    ...
    -0.06
    ÙĪØ¡
    -0.06
    erra
    -0.06
    getting
    -0.06
    POSITIVE LOGITS
    /*@
    0.08
    GLOBALS
    0.07
    å°ı鬼
    0.06
    à®ŀ
    0.06
    STDOUT
    0.06
    汶
    0.06
    æį®
    0.06
     STDOUT
    0.06
     scorn
    0.06
    åĭĥ
    0.06
    Activations Density 0.078%

    No Known Activations