© 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. 4355
    Prev
    Next
    INDEX
    Explanations

    code or 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
     hy
    -0.23
    对çħ§æ£ĢæŁ¥
    -0.21
    æµĵæµĵçļĦ
    -0.20
    èĩªåįij
    -0.20
     actionPerformed
    -0.20
     Hy
    -0.20
    è¿Ľç¨ĭ
    -0.19
    lang
    -0.19
    è°£è¨Ģ
    -0.19
     jeep
    -0.19
    POSITIVE LOGITS
    ;;;;
    0.24
    alyzed
    0.24
    twor
    0.24
    )__
    0.24
    @student
    0.23
    )./
    0.23
     createState
    0.23
    .getWriter
    0.23
    ")));
    0.23
    zik
    0.22
    Activations Density 0.001%

    No Known Activations