© 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. 328
    Prev
    Next
    INDEX
    Explanations

    SQL databases

    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
    ç³Ĺ
    -0.25
     migliori
    -0.23
    _deinit
    -0.22
     siti
    -0.21
     roma
    -0.20
    phalt
    -0.19
     @{$
    -0.19
     hã
    -0.19
    avors
    -0.19
    :both
    -0.19
    POSITIVE LOGITS
    游æĪıæĬĢå·§
    0.23
     SQL
    0.23
    бÑĥÑĢ
    0.22
    bish
    0.21
     gameTime
    0.21
     flashback
    0.20
    .sql
    0.20
    .jdbc
    0.20
    isci
    0.19
    .nextSibling
    0.19
    Activations Density 2.446%

    No Known Activations