© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30097
    Prev
    Next
    INDEX
    Explanations

    language codes

    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
    æķijåĩº
    -0.07
    éĻIJå®ļ
    -0.07
    culus
    -0.07
    žÃŃ
    -0.06
    å°ıé¢ĺ
    -0.06
    ç´ł
    -0.06
    orte
    -0.06
    å½ĵä¹ĭ
    -0.06
    ä»ħæѤ
    -0.06
    /tool
    -0.06
    POSITIVE LOGITS
    é«ĺä½İ
    0.07
    رÙĪÙĬ
    0.07
    æİĴ
    0.07
    oka
    0.07
    ä¸Ģè¿Ľ
    0.07
    èĦī
    0.07
    çľ¼çľĭ
    0.07
    utori
    0.06
    åıijå±ķä¸Ń
    0.06
    amble
    0.06
    Activations Density 0.142%

    No Known Activations