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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 889
    Prev
    Next
    INDEX
    Explanations

    start of line fragments

    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
    "title
    -0.44
    tÃł
    -0.43
    /ay
    -0.43
    *sp
    -0.40
    "label
    -0.40
    [".
    -0.40
    (DBG
    -0.39
    .GetLength
    -0.39
    /Runtime
    -0.39
    "w
    -0.38
    POSITIVE LOGITS
     cerco
    0.50
     disg
    0.45
     lucr
    0.40
     rico
    0.36
    广åijĬæľįåĬ¡
    0.36
     buc
    0.35
     abol
    0.35
     siti
    0.34
     horr
    0.34
    -Owned
    0.34
    Activations Density 10.036%

    No Known Activations