© 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. 17590
    Prev
    Next
    INDEX
    Explanations

    scientific publications

    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
    ilde
    -0.07
    ÏĦÏī
    -0.07
    ovy
    -0.07
    éĢŁåº¦
    -0.07
    é§
    -0.07
    aros
    -0.07
    takt
    -0.07
    产åĵģä»·æł¼
    -0.07
    umpa
    -0.07
    UY
    -0.07
    POSITIVE LOGITS
    à¸Ļà¹Į
    0.07
    coli
    0.07
    ãĤ¥
    0.07
    åĪĢ
    0.07
    çijľ
    0.06
    пен
    0.06
     бÑĢон
    0.06
    æķĮ
    0.06
    çIJ³å¨ľ
    0.06
    mi
    0.06
    Activations Density 0.006%

    No Known Activations