© 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. 3468
    Prev
    Next
    INDEX
    Explanations

    Health and medicine

    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
     }//
    -0.26
     }},↵
    -0.21
    ðŁijĨ
    -0.20
     honda
    -0.20
    phalt
    -0.20
    icensing
    -0.20
     lucr
    -0.20
     trebuie
    -0.19
    raq
    -0.19
    éķ¢
    -0.19
    POSITIVE LOGITS
    ä¼ĹæīĢåij¨
    0.32
    ä¼ĹæīĢåij¨çŁ¥
    0.31
     many
    0.26
    æĪijä»¬çŁ¥éģĵ
    0.26
     modern
    0.24
    éĥ½çŁ¥éģĵ
    0.24
     world
    0.22
     previous
    0.21
     traditional
    0.21
    á¾±
    0.21
    Activations Density 2.003%

    No Known Activations