© 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. 23359
    Prev
    Next
    INDEX
    Explanations

    name suffixes or abbreviations

    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
    åıijçİ°åĴĮ
    -0.07
    над
    -0.06
    dob
    -0.06
    IDGET
    -0.06
     discovery
    -0.06
    欢è¿İæĤ¨çļĦ
    -0.06
    ian
    -0.06
    ãģĭãģŃ
    -0.06
    eneric
    -0.06
    ier
    -0.06
    POSITIVE LOGITS
    uret
    0.08
    å¿ħ须注æĺİ
    0.07
    说æĺİäºĨ
    0.07
    ä¸İ伦
    0.07
    uring
    0.07
    表æĺİäºĨ
    0.07
    arra
    0.07
    ÄĻd
    0.07
    è·Łéŀĭ
    0.07
    marker
    0.07
    Activations Density 0.018%

    No Known Activations