© 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. 775
    Prev
    Next
    INDEX
    Explanations

    specific 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
    <fieldset
    -0.22
    .epam
    -0.21
    ıp
    -0.21
    ibraltar
    -0.20
    bish
    -0.20
    <GameObject
    -0.20
    Outlet
    -0.19
    lj
    -0.19
     Geli
    -0.18
    .AttributeSet
    -0.18
    POSITIVE LOGITS
    urrenc
    0.22
    strtolower
    0.21
    irates
    0.21
    monton
    0.20
    åħ¨èµĦåŃIJ
    0.20
     OTHERWISE
    0.20
    tility
    0.20
    ycin
    0.19
     Rarity
    0.19
    clusão
    0.19
    Activations Density 0.002%

    No Known Activations