© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 526
    Prev
    Next
    INDEX
    Explanations

    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
    ãģıãĤĵ
    -0.21
    ?>↵↵↵
    -0.20
    .RegularExpressions
    -0.20
    EXPECT
    -0.19
    çĶ¨å¾®ä¿¡
    -0.19
    å£ģ纸
    -0.19
     )}↵↵
    -0.19
    åľ¨åħ¶
    -0.18
    .BO
    -0.18
    och
    -0.18
    POSITIVE LOGITS
    .getOwnProperty
    0.30
    ".↵↵↵↵
    0.25
    pson
    0.24
     )↵↵↵↵↵↵↵↵
    0.23
    yla
    0.23
    eor
    0.23
     bacheca
    0.23
     MediaQuery
    0.22
    spiel
    0.22
     FetchType
    0.21
    Activations Density 0.001%

    No Known Activations