© 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. 2570
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    jsonp
    -0.20
     inform
    -0.19
    åİŁåĪĻä¸Ĭ
    -0.18
    ä»Ģä¹Īåij¢
    -0.18
     ``
    -0.18
    ãĥªãĥ³
    -0.18
    ByUrl
    -0.18
    “
    -0.17
    åģľçķĻåľ¨
    -0.17
     “
    -0.17
    POSITIVE LOGITS
    möglich
    0.24
    뾸
    0.21
     }};↵
    0.20
    çļĽ
    0.20
    stk
    0.20
    orting
    0.20
    webElementXpaths
    0.20
    nection
    0.20
    wargs
    0.20
    (preg
    0.20
    Activations Density 0.011%

    No Known Activations