© 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. 40674
    Prev
    Next
    INDEX
    Explanations

    instance or eg followed by punctuation

    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
    nä
    -0.09
    ripper
    -0.09
    ensibly
    -0.09
    iante
    -0.09
    edata
    -0.09
    ahuan
    -0.08
    .AI
    -0.08
    edBy
    -0.08
    egos
    -0.08
    sse
    -0.08
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.11
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.09
    :
    0.09
     اÛĮÙĨÚ©Ùĩ
    0.08
    ,
    0.08
    ï¼ļ
    0.08
    forth
    0.08
    2
    0.07
    éĩĩçĶ¨
    0.07
    æĪijåIJ§
    0.07
    Activations Density 0.002%

    No Known Activations