© 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. 47201
    Prev
    Next
    INDEX
    Explanations

    spacing or interval

    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
    iscos
    -0.09
    eam
    -0.08
    åĽ
    -0.07
     Dummy
    -0.07
    iew
    -0.07
    .alloc
    -0.07
    zilla
    -0.07
    ØŃاء
    -0.07
    WithTitle
    -0.07
    _locals
    -0.07
    POSITIVE LOGITS
    éĹ´éļĶ
    0.17
    éĹ´è·Ŀ
    0.16
     spacing
    0.15
    spacing
    0.14
     distance
    0.13
    Spacing
    0.12
    è·Ŀ离
    0.12
    ä¹ĭéĹ´çļĦè·Ŀ离
    0.12
    缸éļĶ
    0.12
    _spacing
    0.12
    Activations Density 0.054%

    No Known Activations