© 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. 3193
    Prev
    Next
    INDEX
    Explanations

    mixed language and code

    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
    ofilm
    -0.21
    actionDate
    -0.21
    permalink
    -0.21
    antry
    -0.20
     stringWith
    -0.20
     PureComponent
    -0.20
    .UserInfo
    -0.20
     Mech
    -0.20
    çĽ
    -0.19
    (disposing
    -0.19
    POSITIVE LOGITS
    æľĭåıĭ们对
    0.20
    詹
    0.19
     vej
    0.19
     Wass
    0.18
    è¿Ļ两ç§į
    0.18
     RA
    0.18
     OSError
    0.18
    _then
    0.17
    chia
    0.17
    _keyword
    0.17
    Activations Density 0.001%

    No Known Activations