© 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
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 627
    Prev
    Next
    INDEX
    Explanations

    names and brands

    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
    åĭł
    -0.33
    полниÑĤÑĮ
    -0.29
    åľ¨è¿ĩ渡
    -0.29
     ÑģоÑĩеÑĤа
    -0.28
    é¾ĩ
    -0.28
    ç½ijç«Ļé¦ĸ页
    -0.28
    éħ½
    -0.27
    еÑģÑĤеÑģÑĤв
    -0.27
    åĴ»
    -0.27
    Haunted
    -0.27
    POSITIVE LOGITS
    raits
    0.29
    datable
    0.27
    Disappear
    0.27
    ancellable
    0.26
    rightness
    0.26
    (Have
    0.26
    -cigarettes
    0.26
    oriously
    0.26
    folios
    0.26
    pson
    0.25
    Activations Density 8.263%

    No Known Activations