© 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. 40666
    Prev
    Next
    INDEX
    Explanations

    tables, charts, curves, maps

    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
     aktif
    -0.08
    _signature
    -0.08
    setUp
    -0.08
    RGBA
    -0.08
    ovel
    -0.08
    opat
    -0.07
    olim
    -0.07
    æŀIJ
    -0.07
    æ½ľåľ¨
    -0.07
    çĻ¾èįī
    -0.07
    POSITIVE LOGITS
     tables
    0.11
     lookup
    0.11
    lookup
    0.10
    tables
    0.10
     Lookup
    0.10
    Tables
    0.10
    charts
    0.09
     tab
    0.09
     charts
    0.09
     chart
    0.09
    Activations Density 0.043%

    No Known Activations