© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4365
    Prev
    Next
    INDEX
    Explanations

    programming and technical

    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
    Negative Logits
    uguay
    -0.21
    rescia
    -0.20
    unto
    -0.20
    .SwingConstants
    -0.20
    "]=="
    -0.19
    ussia
    -0.19
    "]."
    -0.19
    åij¼ãģ°ãĤĮ
    -0.19
    ожеÑĤ
    -0.19
    éparation
    -0.18
    POSITIVE LOGITS
    æ·ĺæ±°
    0.20
    "%
    0.19
    itizer
    0.19
    åľ°æĸ¹
    0.19
     roma
    0.19
    .Conn
    0.19
     Dungeons
    0.18
    èį¼
    0.18
    æģ¯
    0.18
    tes
    0.18
    Activations Density 0.013%

    No Known Activations