© 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. 2852
    Prev
    Next
    INDEX
    Explanations

    technical or 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
     besten
    -0.21
    assen
    -0.20
    ıl
    -0.19
    (DEBUG
    -0.19
     CONSTANTS
    -0.18
     calf
    -0.18
     StringComparison
    -0.18
    MUX
    -0.18
    CI
    -0.18
     propriétaire
    -0.18
    POSITIVE LOGITS
    大åŀĭå¤ļ人
    0.27
    -describedby
    0.24
     dra
    0.24
    .MouseAdapter
    0.24
    .CustomButton
    0.23
    家éĥ½çŁ¥éģĵ
    0.23
    åĽ¹
    0.23
    bsite
    0.22
    纪å§ĶçĽij
    0.22
    -strokes
    0.22
    Activations Density 0.001%

    No Known Activations