© 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. 56166
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers or boolean

    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
    º
    -0.07
    沦
    -0.07
    åĬ¨è¾Ħ
    -0.06
    à§ĭধ
    -0.06
    ä½Ĩä¸įéĻIJäºİ
    -0.06
    好似
    -0.06
    æ¯ıæ¯ı
    -0.06
    è¾īæĺł
    -0.06
    .lex
    -0.06
    .Marshal
    -0.06
    POSITIVE LOGITS
    intas
    0.07
    yr
    0.07
     Bundy
    0.07
    wati
    0.07
     unthinkable
    0.07
    åģ¶
    0.07
    åłª
    0.06
    ове
    0.06
    ektor
    0.06
    ede
    0.06
    Activations Density 0.013%

    No Known Activations