© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 790
    Prev
    Next
    INDEX
    Explanations

    communication or information

    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
    çķĻè¨ĢæĿ¿
    -0.31
    åıĭæĥħéĵ¾æİ¥
    -0.30
    åľ¨è¿ĩæ¸¡æľŁ
    -0.28
    æŁ¥çľĭ详æĥħ
    -0.28
     homers
    -0.26
     yOffset
    -0.25
     topLeft
    -0.24
     centerX
    -0.23
     scaleX
    -0.23
    è¯Ł
    -0.23
    POSITIVE LOGITS
    ðŁĵIJ
    0.34
     libertin
    0.30
    âļĹ
    0.30
    -send
    0.27
    (Throwable
    0.26
    ={"/
    0.26
    geries
    0.26
    çĶµè¯Ŀ
    0.25
    æ²ŁéĢļ
    0.25
     glyphicon
    0.25
    Activations Density 3.778%

    No Known Activations