© 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. 3371
    Prev
    Next
    INDEX
    Explanations

    say "?"

    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
    髯
    -0.21
    ç¾°
    -0.20
    cuador
    -0.20
    .SizeMode
    -0.19
    ç½ijé¦ĸ页
    -0.19
    íĤ´
    -0.19
    ulings
    -0.19
    aycast
    -0.19
    rän
    -0.19
     tph
    -0.18
    POSITIVE LOGITS
    æŶ
    0.22
     ?
    0.21
     {č↵č↵č↵
    0.20
    çļĦä¸Ģ项
    0.20
     novitÃł
    0.19
    æİİ
    0.19
    .pageY
    0.19
    OPLE
    0.19
    LoadIdentity
    0.19
    æĹ¶è¡¨ç¤º
    0.18
    Activations Density 0.056%

    No Known Activations