© 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. 2084
    Prev
    Next
    INDEX
    Explanations

    text fragments

    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
    InlineData
    -0.19
    èĭĶ
    -0.19
    çľĭä¸įæĩĤ
    -0.18
    acid
    -0.18
     multer
    -0.18
     меÑĤалл
    -0.18
    sg
    -0.18
     Barn
    -0.18
    Ĥ¬
    -0.17
    سد
    -0.17
    POSITIVE LOGITS
    opleft
    0.23
    IGHL
    0.22
    æ²¾
    0.22
     Tüm
    0.21
    {/*
    0.21
    osemite
    0.20
    ForMember
    0.20
    naments
    0.20
    aycast
    0.20
    eurs
    0.20
    Activations Density 0.006%

    No Known Activations