© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2305
    Prev
    Next
    INDEX
    Explanations

    named entities technical jargon

    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
     Guzzle
    -0.22
    *****/↵
    -0.20
    $/,↵
    -0.20
    -caret
    -0.20
    __':č↵
    -0.19
    mite
    -0.19
    è¹ĭ
    -0.19
    nad
    -0.18
    饯
    -0.18
    cej
    -0.18
    POSITIVE LOGITS
     Shorts
    0.20
    èĪ¯
    0.19
    æķĻèĤ²èµĦæºIJ
    0.19
     potrÃł
    0.19
    columnName
    0.18
    retorno
    0.18
    INY
    0.18
    輪
    0.18
     Canadiens
    0.18
    à¸Ńà¸Ļาà¸Ħ
    0.18
    Activations Density 0.001%

    No Known Activations