© 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. 9966
    Prev
    Next
    INDEX
    Explanations

    inclusion of studies

    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
    afari
    -0.08
     independently
    -0.08
    cion
    -0.08
    oce
    -0.07
    åIJįåī¯
    -0.07
    æ±°
    -0.07
    kbd
    -0.07
    Independ
    -0.07
    ookie
    -0.07
    ObjectOfType
    -0.07
    POSITIVE LOGITS
     inclusion
    0.10
     inclusive
    0.10
     inclus
    0.10
     included
    0.10
    åľ¨åĨħçļĦ
    0.09
    INCLUDE
    0.09
    (include
    0.09
    纳åħ¥
    0.09
    inclusive
    0.09
     includ
    0.08
    Activations Density 0.045%

    No Known Activations