© 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. 4039
    Prev
    Next
    INDEX
    Explanations

    technical or 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
     piger
    -0.24
    å±IJ
    -0.22
    -addons
    -0.21
    Filed
    -0.21
    -eslint
    -0.21
     (*((
    -0.21
    readcr
    -0.20
    .AllowUser
    -0.20
    {return
    -0.20
    #Region
    -0.20
    POSITIVE LOGITS
    ="{!!
    0.23
    ICollectionView
    0.19
     Extr
    0.19
     spoiler
    0.19
    icut
    0.19
    ɹ
    0.19
     })();↵
    0.18
    éĴ¦
    0.18
     "'.
    0.18
    ports
    0.18
    Activations Density 0.001%

    No Known Activations