© 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. 1714
    Prev
    Next
    INDEX
    Explanations

    greater less

    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
    Nguá»ĵn
    -0.29
    :both
    -0.27
    **)&
    -0.25
    ----------------------------------------------------------------------↵
    -0.24
    -valu
    -0.23
    -deals
    -0.23
     (*((
    -0.23
    yw
    -0.23
    -scalable
    -0.23
     earthqu
    -0.23
    POSITIVE LOGITS
    è¶ħè¿ĩ
    0.35
     higher
    0.35
    æİ¥è¿ij
    0.35
    大äºİ
    0.34
     high
    0.32
    ä¸ĭéĿ¢æĺ¯å°ı
    0.32
    å°ıäºİ
    0.32
     close
    0.32
     greater
    0.32
     below
    0.31
    Activations Density 2.668%

    No Known Activations