© 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. 10638
    Prev
    Next
    INDEX
    Explanations

    used to inform or state facts

    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
     uncomment
    -0.07
    çī¹å¼Ĥ
    -0.07
    ä¸įçĿĢ
    -0.06
    jang
    -0.06
     referencing
    -0.06
     supposedly
    -0.06
     zacz
    -0.06
    åĽłä¸ºå®ĥ
    -0.06
    .undefined
    -0.06
    æĪij第ä¸Ģ次
    -0.06
    POSITIVE LOGITS
     bahwa
    0.17
     rằng
    0.15
     bahawa
    0.14
    à¹Ħà¸Ķà¹īวà¹Īา
    0.13
     ÏĮÏĦι
    0.12
     faptul
    0.12
     بأÙĨ
    0.10
    à¸Ĺราà¸ļวà¹Īา
    0.10
     Ø£ÙİÙĨÙİÙij
    0.10
    表æĺİ
    0.09
    Activations Density 0.440%

    No Known Activations