© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1529
    Prev
    Next
    INDEX
    Explanations

    code related terms

    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
    mite
    -0.22
    HeaderInSection
    -0.20
    饧
    -0.20
     Schwarz
    -0.19
    =\'
    -0.18
    GetSize
    -0.18
    ?family
    -0.18
    vest
    -0.18
    ëĥĪ
    -0.17
    adius
    -0.17
    POSITIVE LOGITS
     UITableViewController
    0.25
    .OrderByDescending
    0.24
    bilit
    0.23
    /stream
    0.22
     CreateTable
    0.22
    rowable
    0.21
    ali
    0.21
    /vendors
    0.21
    çĩł
    0.20
     Gór
    0.20
    Activations Density 0.626%

    No Known Activations