© 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. 3410
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    *)_
    -0.24
    -fw
    -0.23
    .firebaseapp
    -0.22
    .InnerException
    -0.22
    UserController
    -0.22
    trys
    -0.21
    CastException
    -0.20
    -serif
    -0.20
    ::$_
    -0.20
    thinkable
    -0.20
    POSITIVE LOGITS
    å¯Ŀ
    0.20
    ç½ijåıĭè¯Ħ论
    0.20
    踹
    0.20
     ******************************************************************************↵
    0.20
    æĬĹè¡¡
    0.20
    ãİľ
    0.20
     bruk
    0.19
     Pickup
    0.19
    æijĩäºĨ
    0.19
    åĸ³
    0.19
    Activations Density 0.278%

    No Known Activations