© 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. 1664
    Prev
    Next
    INDEX
    Explanations

    first

    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
    issan
    -0.25
     Clintons
    -0.24
    Prosec
    -0.23
     weekdays
    -0.22
     wholesalers
    -0.21
     verschied
    -0.21
     franchises
    -0.21
    游æĪıè§Ĵèī²
    -0.21
     difÃŃc
    -0.21
    outers
    -0.21
    POSITIVE LOGITS
    -last
    0.33
    arily
    0.28
    对åħ¶çľŁå®ŀ
    0.26
    half
    0.25
     оÑĩеÑĢедÑĮ
    0.25
    -order
    0.24
    <small
    0.24
    .skin
    0.23
    few
    0.23
    <textarea
    0.23
    Activations Density 1.063%

    No Known Activations