© 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. 60714
    Prev
    Next
    INDEX
    Explanations

    definition or definitions

    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
    otec
    -0.10
    ouser
    -0.09
    ForObject
    -0.08
    ecat
    -0.08
    ÅŁe
    -0.08
    atee
    -0.07
    è·¯éĢı
    -0.07
    .ON
    -0.07
    oming
    -0.07
    shaw
    -0.07
    POSITIVE LOGITS
     definitions
    0.11
    Definitions
    0.09
     Definitions
    0.09
    çļĦå®ļä¹ī
    0.09
    inition
    0.09
    definitions
    0.08
     definition
    0.08
    Definition
    0.08
    å®ļä¹ī
    0.08
     Definition
    0.08
    Activations Density 0.009%

    No Known Activations