© 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. 3439
    Prev
    Next
    INDEX
    Explanations

    #

    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
    ãģįãĤĮ
    -0.31
    IGGER
    -0.27
    åĪ©çĶ¨æĤ¨çļĦ
    -0.26
    ollapsed
    -0.26
    qli
    -0.26
    eggies
    -0.25
    è¾¼ãĤģ
    -0.25
    olicited
    -0.24
    alyzed
    -0.23
    ookies
    -0.23
    POSITIVE LOGITS
    ergus
    0.30
    myModal
    0.30
    exampleModal
    0.28
    .SetParent
    0.28
    IMPLIED
    0.26
    кле
    0.24
    GetSize
    0.23
    -Owned
    0.23
    .AppSettings
    0.23
    ulfilled
    0.22
    Activations Density 0.118%

    No Known Activations