© 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. 3095
    Prev
    Next
    INDEX
    Explanations

    WARRANTIES

    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
    SingleOrDefault
    -0.27
    çīĪæĿĥå½ĴåİŁ
    -0.22
    CompleteListener
    -0.21
    ViewChild
    -0.20
    ector
    -0.19
    .Accessible
    -0.19
    忪
    -0.19
     zoekt
    -0.19
    -txt
    -0.19
    UserCode
    -0.19
    POSITIVE LOGITS
    /***/
    0.27
    /Dk
    0.23
    aeda
    0.22
    %"><
    0.22
    ]={↵
    0.22
    é«Ģ
    0.21
    DMETHOD
    0.21
    =findViewById
    0.21
    YO
    0.20
    .Sin
    0.20
    Activations Density 0.023%

    No Known Activations