© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen2.5-7B-IT
    3. 20-MATRYOSHKA-65K
    4. 1166
    Prev
    Next
    INDEX
    Explanations

    math and physics terms

    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
    âģİ
    -0.26
    indsight
    -0.25
    .createFrom
    -0.24
    OffsetTable
    -0.23
    =localhost
    -0.23
    InitStruct
    -0.23
     )↵↵↵↵↵↵↵↵
    -0.22
    вÑĪей
    -0.21
    .slim
    -0.21
    ={({
    -0.21
    POSITIVE LOGITS
    alties
    0.24
     careg
    0.23
     =======
    0.22
    çīĪæĿĥå½ĴåİŁ
    0.22
    é¨Ļ
    0.22
     Affiliate
    0.22
     councillor
    0.21
    个å¤ļæľĪ
    0.21
    ampton
    0.20
    çļĦ带é¢Ĩ
    0.20
    Activations Density 0.296%

    No Known Activations