© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15936
    Prev
    Next
    INDEX
    Explanations

    transformations, conversions, filtering

    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
    -setup
    -0.09
    agher
    -0.08
    Setup
    -0.08
    _callbacks
    -0.07
    _ENUM
    -0.07
    åĪĽå»ºæ´»åĬ¨
    -0.07
     Setup
    -0.07
    éļĻ
    -0.07
     setup
    -0.07
    enumer
    -0.07
    POSITIVE LOGITS
     transformation
    0.16
     transform
    0.14
     Transformation
    0.13
    Transformation
    0.13
     transformations
    0.13
     transforming
    0.13
     Transform
    0.12
    transform
    0.12
    -transform
    0.12
     transforms
    0.12
    Activations Density 0.194%

    No Known Activations