© 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. 2780
    Prev
    Next
    INDEX
    Explanations

    understand

    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
    ChildIndex
    -0.23
    kontakte
    -0.23
    ieties
    -0.22
    stÄĻp
    -0.22
    chestra
    -0.22
    pleted
    -0.21
    uely
    -0.21
    æĹ®
    -0.21
    èĵĬ
    -0.21
    roupon
    -0.21
    POSITIVE LOGITS
    æŁ¥çľĭ详æĥħ
    0.27
     ìĿ´íķ´
    0.26
    ç½ijç«Ļé¦ĸ页
    0.25
    çĤºä»Ģ麼
    0.25
    åıĭæĥħéĵ¾æİ¥
    0.25
    æĸ°åĬł
    0.24
    çļĦçIJĨ解
    0.23
    ä»İæł¹æľ¬
    0.23
    åħ³äºİæĪij们
    0.23
    Explanation
    0.23
    Activations Density 0.166%

    No Known Activations