© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2019
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     strncmp
    -0.26
     adoles
    -0.25
     componentDidUpdate
    -0.24
    idUser
    -0.24
     $$$
    -0.24
     {?}
    -0.23
     miglior
    -0.23
    为äºĨæĽ´å¥½
    -0.23
    å¤įå·¥å¤į
    -0.22
     componentWill
    -0.22
    POSITIVE LOGITS
    oriously
    0.36
     print
    0.24
     my
    0.24
    :<?
    0.24
    umblr
    0.23
     addObserver
    0.23
    #Region
    0.23
    alli
    0.22
    alamat
    0.21
    举æĸ¹è´¢å¯Į
    0.21
    Activations Density 6.188%

    No Known Activations