© 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. 15063
    Prev
    Next
    INDEX
    Explanations

    file paths and revisions

    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
    orda
    -0.08
    -bot
    -0.08
     toArray
    -0.08
    åŃ¦ä¹łåĪ°
    -0.07
    sto
    -0.07
    azzi
    -0.07
    .VK
    -0.07
    å±ħæĺĵ
    -0.07
    为é¦ĸ
    -0.07
    举èĩ³
    -0.07
    POSITIVE LOGITS
    é«
    0.06
    revision
    0.06
    licer
    0.06
    çĻ½é©¬
    0.06
    xffffffff
    0.06
    Revision
    0.06
     Modifications
    0.06
    ÙĪÙģ
    0.06
    .er
    0.06
    çĿĽ
    0.05
    Activations Density 0.033%

    No Known Activations