© 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. 2490
    Prev
    Next
    INDEX
    Explanations

    forms of to be

    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
    .metro
    -0.24
    Matchers
    -0.23
    "w
    -0.20
    raud
    -0.20
    /↵↵↵↵
    -0.20
    ernen
    -0.20
    overe
    -0.19
    utral
    -0.19
    .apiUrl
    -0.19
     âĵĺ
    -0.19
    POSITIVE LOGITS
     Kardash
    0.23
     appré
    0.23
    .PrintWriter
    0.22
     Padres
    0.22
     tako
    0.20
    é£Łãģ¹ãģ¦
    0.20
    تظ
    0.20
     <!--[
    0.20
    \Blueprint
    0.19
     Flavor
    0.19
    Activations Density 0.615%

    No Known Activations