© 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. 41749
    Prev
    Next
    INDEX
    Explanations

    equations and models

    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
    erop
    -0.07
    ifix
    -0.07
    issan
    -0.07
    evas
    -0.07
    Finder
    -0.07
    骼
    -0.07
    GeV
    -0.07
     phép
    -0.07
    ä¸Ģçķª
    -0.07
    Fix
    -0.07
    POSITIVE LOGITS
     modeling
    0.11
    建模
    0.11
     models
    0.11
     integ
    0.10
     modelling
    0.10
     equations
    0.10
     Modeling
    0.09
     model
    0.09
     Models
    0.09
     dynamics
    0.09
    Activations Density 0.063%

    No Known Activations