© 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. 55408
    Prev
    Next
    INDEX
    Explanations

    problem or question description

    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
    çļĦç»ıéªĮ
    -0.07
    /cop
    -0.07
    ä¹ł
    -0.07
    æ¼ĶçļĦ
    -0.07
    AVA
    -0.07
    ئا
    -0.07
    ocoa
    -0.07
    cellent
    -0.07
    沸
    -0.06
    FileType
    -0.06
    POSITIVE LOGITS
    راÙĩ
    0.07
    liku
    0.07
    éĢļãĤĬãģ«
    0.07
    æģķ
    0.06
     htt
    0.06
     OPTIONS
    0.06
    onna
    0.06
     basically
    0.06
    Ñģен
    0.06
    otron
    0.06
    Activations Density 0.022%

    No Known Activations