© 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. 3142
    Prev
    Next
    INDEX
    Explanations

    code related terms

    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
    обоÑĢ
    -0.21
    Ĭ¶
    -0.20
    /apis
    -0.19
    éĻªåIJĮ
    -0.19
     ver
    -0.19
     оÑĤмеÑĤиÑĤÑĮ
    -0.18
    INavigation
    -0.18
    çĿİ
    -0.18
    .ver
    -0.18
    .setViewport
    -0.18
    POSITIVE LOGITS
     addCriterion
    0.22
    incinn
    0.21
    )throws
    0.21
    forgettable
    0.20
    emean
    0.20
    ']]['
    0.20
    });↵↵↵↵
    0.20
    alborg
    0.19
    _graphics
    0.19
    =admin
    0.19
    Activations Density 0.001%

    No Known Activations