© 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. 47
    Prev
    Next
    INDEX
    Explanations

    exact

    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
     Clintons
    -0.35
     endors
    -0.34
     enthus
    -0.33
    eparator
    -0.33
    è¿°èģĮ
    -0.31
    icens
    -0.30
    urnished
    -0.30
    ãĥ¦ãĥ¼
    -0.30
    orsche
    -0.30
    对çħ§æ£ĢæŁ¥
    -0.28
    POSITIVE LOGITS
    evento
    0.28
    é£Łãģ¹ãģ¦
    0.27
     desper
    0.27
    é£Łãģ¹ãģŁ
    0.25
     resil
    0.24
     krij
    0.23
     ull
    0.23
     kijken
    0.23
     desi
    0.22
    Salvar
    0.22
    Activations Density 11.025%

    No Known Activations