© 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. 4080
    Prev
    Next
    INDEX
    Explanations

    code and technical text

    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
    sim
    -0.20
    æĥĽ
    -0.20
    _plugins
    -0.19
    umnos
    -0.19
    ornment
    -0.18
    _construct
    -0.18
    å¸Ļ
    -0.18
     builtin
    -0.18
    说æĪij
    -0.18
     groin
    -0.18
    POSITIVE LOGITS
    rets
    0.24
     bénéficie
    0.24
    ç»Ĺ
    0.22
     spécialisé
    0.21
     merch
    0.20
    -links
    0.19
    á»İ
    0.19
     vandal
    0.18
    .StoredProcedure
    0.18
    rames
    0.18
    Activations Density 0.005%

    No Known Activations