© 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. 2251
    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
    gnore
    -0.26
    åij¼åĴĮ
    -0.25
    ç¡ķ士çłĶ究
    -0.24
    aeda
    -0.23
    èĻķçIJĨåıĬ
    -0.23
    çݩ家æľĭåıĭ
    -0.22
    çıµ
    -0.22
    æĭľå¸ĪåѦèīº
    -0.22
     AsyncStorage
    -0.22
    åĢŀ
    -0.22
    POSITIVE LOGITS
    eslint
    0.20
    ver
    0.20
     démarche
    0.19
    çıĬ
    0.18
     Christ
    0.18
    ãĤµãĥŃãĥ³
    0.18
    /********
    0.18
     Bal
    0.18
    <?=
    0.18
    vert
    0.17
    Activations Density 0.015%

    No Known Activations