© 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. 3429
    Prev
    Next
    INDEX
    Explanations

    business technical legal

    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
    )init
    -0.24
    被èªī
    -0.23
    è¿ĶåĽŀæIJľçĭIJ
    -0.22
    建档ç«ĭ
    -0.21
    ðŁļ©
    -0.20
    墨西
    -0.20
     [~,
    -0.20
    .struts
    -0.20
    âĸ·
    -0.19
     resil
    -0.19
    POSITIVE LOGITS
    åħ¼
    0.22
    anim
    0.21
    lox
    0.19
    romise
    0.19
    tep
    0.18
     =>'
    0.18
    axies
    0.17
     Xiaomi
    0.17
    .Retrofit
    0.17
    chef
    0.17
    Activations Density 0.001%

    No Known Activations