© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3100
    Prev
    Next
    INDEX
    Explanations

    to

    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
    toISOString
    -0.22
    GPC
    -0.19
    ily
    -0.19
    ulfill
    -0.19
    .setTag
    -0.19
    Helvetica
    -0.19
     Cav
    -0.18
    é£Łãģ¹ãģŁ
    -0.18
    urile
    -0.18
    rip
    -0.18
    POSITIVE LOGITS
    eggies
    0.26
     Erotik
    0.25
    szÄĻ
    0.24
    inidad
    0.23
    .getBounds
    0.23
     erotisch
    0.23
    สามาร
    0.23
    klä
    0.22
    -League
    0.22
    VERRIDE
    0.22
    Activations Density 0.001%

    No Known Activations