© 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. 4069
    Prev
    Next
    INDEX
    Explanations

    use/usage

    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
     bufsize
    -0.22
    odka
    -0.21
    註
    -0.20
    訪ãĤĮ
    -0.20
    kening
    -0.20
    kish
    -0.20
    elsea
    -0.20
    _HERSHEY
    -0.20
    terminated
    -0.20
    /sidebar
    -0.20
    POSITIVE LOGITS
     usage
    0.38
     Usage
    0.36
    usage
    0.33
    Usage
    0.31
    使çĶ¨
    0.27
    .usage
    0.26
    _usage
    0.26
     uso
    0.26
    .Usage
    0.24
     use
    0.23
    Activations Density 0.452%

    No Known Activations