© 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. 3844
    Prev
    Next
    INDEX
    Explanations

    technical 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
    влажн
    -0.23
    -With
    -0.21
    è®°èĢħäºĨ解
    -0.20
    intptr
    -0.20
    -angular
    -0.20
    ðŁ¥ĩ
    -0.20
    _MetaData
    -0.20
    isko
    -0.20
    äge
    -0.19
    okedex
    -0.19
    POSITIVE LOGITS
    _Util
    0.20
     diseñador
    0.20
    typeName
    0.19
    .Dao
    0.19
     Guzzle
    0.19
     nắm
    0.18
    å°ıå°ı
    0.18
     sesso
    0.18
    LOS
    0.18
     empres
    0.18
    Activations Density 0.001%

    No Known Activations