© 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. 2534
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    scrição
    -0.27
    "nil
    -0.24
    oproject
    -0.24
    }());↵
    -0.23
     ++;↵
    -0.21
     beneficiation
    -0.21
    .SingleOrDefault
    -0.21
    iage
    -0.20
    urrect
    -0.20
    @student
    -0.20
    POSITIVE LOGITS
    Türkiye
    0.23
    {{--
    0.20
     ucwords
    0.19
    cheap
    0.19
    ç²Ĵ
    0.18
    ud
    0.18
    ç¯ĵ
    0.18
    ç¨Ĺ
    0.17
     />\
    0.17
     grav
    0.17
    Activations Density 0.126%

    No Known Activations