© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2574
    Prev
    Next
    INDEX
    Explanations

    technical snippets

    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
     NotSupportedException
    -0.22
    .charCodeAt
    -0.21
    èıĢ
    -0.19
    èħł
    -0.19
    ()){
    -0.19
    .listView
    -0.19
    éĶĴ
    -0.19
    æ®
    -0.19
     cellForRowAtIndexPath
    -0.19
    ê¹Ŀ
    -0.18
    POSITIVE LOGITS
    herits
    0.26
     HtmlWebpackPlugin
    0.25
    ä¹į
    0.23
    ólogo
    0.22
    edb
    0.20
    urrenc
    0.20
    âīħ
    0.20
    缩
    0.19
    أخÙĪ
    0.19
    oriously
    0.19
    Activations Density 0.009%

    No Known Activations