© 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. 145
    Prev
    Next
    INDEX
    Explanations

    descriptions of concepts

    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
    traî
    -0.25
    аблиÑĨ
    -0.25
    éŃĩ
    -0.23
     замеÑĩа
    -0.22
    å§Ķç»Ħç»ĩ
    -0.22
    помн
    -0.22
    iếu
    -0.21
    æľĭåıĭ们对
    -0.21
    \uD
    -0.20
    voie
    -0.20
    POSITIVE LOGITS
    .ToShort
    0.27
     ninete
    0.27
    ç¾İåªĴ
    0.26
    æĨ
    0.24
    åī
    0.23
    å®ŀäºĭæ±Ĥ
    0.23
    Türkiye
    0.23
    é¬Ī
    0.23
    çĭ·
    0.22
    |required
    0.22
    Activations Density 10.228%

    No Known Activations