© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3060
    Prev
    Next
    INDEX
    Explanations

    databases

    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
    该项
    -0.20
    游æĪıæĵįä½ľ
    -0.20
    _transaksi
    -0.20
     plage
    -0.20
    stddef
    -0.19
    éĺħ读åħ¨æĸĩ
    -0.19
    ç¿ĺ
    -0.19
    æļ´è·Į
    -0.19
    æªIJ
    -0.18
     newly
    -0.18
    POSITIVE LOGITS
    ornment
    0.26
    /Peak
    0.22
    -League
    0.22
    ambia
    0.22
     ePub
    0.22
    ANDOM
    0.21
    !=(
    0.21
     Shine
    0.21
    thane
    0.20
    ?family
    0.20
    Activations Density 0.230%

    No Known Activations