© 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. 3730
    Prev
    Next
    INDEX
    Explanations

    complex text 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
    ðŁĶĴ
    -0.22
     Hã
    -0.22
    تضÙħÙĨ
    -0.21
    ðŁ¤Ķ
    -0.21
    .Glide
    -0.20
    å½Ĵå±ŀäºİ
    -0.20
    Leaks
    -0.20
    utomation
    -0.20
     {\↵
    -0.19
    reste
    -0.19
    POSITIVE LOGITS
    estroy
    0.21
    rador
    0.20
    ovenant
    0.19
    ök
    0.19
    uib
    0.18
    èĩªæĿ¥
    0.18
    .Areas
    0.17
    enguin
    0.17
    .valid
    0.17
     slo
    0.17
    Activations Density 0.001%

    No Known Activations