© 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. 3838
    Prev
    Next
    INDEX
    Explanations

    code and technical text

    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
    ore
    -0.20
    NAMESPACE
    -0.20
     Bray
    -0.19
    ç½ijç«Ļé¦ĸ页
    -0.19
    .CG
    -0.19
    AUTHORIZED
    -0.19
     actionTypes
    -0.19
    驸
    -0.19
     ActionTypes
    -0.18
    ðŁı¼
    -0.18
    POSITIVE LOGITS
    ificate
    0.23
    illis
    0.21
    phoon
    0.21
    yny
    0.21
    )sender
    0.21
    olesale
    0.20
    ypse
    0.20
    apg
    0.20
    abbix
    0.20
    illé
    0.20
    Activations Density 0.001%

    No Known Activations