© 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. 138
    Prev
    Next
    INDEX
    Explanations

    underscore

    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
     enthus
    -0.28
    rowable
    -0.26
    //=
    -0.25
    Æ°á»Ł
    -0.24
    mainwindow
    -0.23
     krist
    -0.23
     Franç
    -0.23
     protester
    -0.22
     taraf
    -0.22
    ajs
    -0.22
    POSITIVE LOGITS
     ×Ķ×ķ×ĵ
    0.31
    FetchRequest
    0.23
    åĵĶ
    0.23
     isAdmin
    0.22
    èī¾æ»ĭ
    0.22
    æľīçļĦçݩ家
    0.21
    ÙĤدÙĬر
    0.21
    çļ®èĤ¤çĹħ
    0.21
     __________________↵↵
    0.20
    çľ¼è¢ĭ
    0.20
    Activations Density 0.249%

    No Known Activations