© 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. 4079
    Prev
    Next
    INDEX
    Explanations

    programming/code

    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
    elsen
    -0.22
     slik
    -0.22
    entiful
    -0.22
    [System
    -0.21
    ahu
    -0.20
     NavParams
    -0.20
    &)↵
    -0.20
    åıĹ
    -0.19
    \views
    -0.18
    &);↵↵
    -0.18
    POSITIVE LOGITS
    .removeListener
    0.23
    åıĭæĥħéĵ¾æİ¥
    0.23
    建档ç«ĭ
    0.22
    .FileNotFoundException
    0.22
    BAB
    0.22
    QUIRES
    0.20
     BCH
    0.20
     Belgi
    0.20
     form
    0.19
    éĿ¢è²Į
    0.19
    Activations Density 0.014%

    No Known Activations