© 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. 1781
    Prev
    Next
    INDEX
    Explanations

    high

    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
    تسÙħ
    -0.22
    bursement
    -0.21
    essages
    -0.20
    æ¼ī
    -0.20
    uffers
    -0.19
    NotSupportedException
    -0.19
    rikes
    -0.18
    æĢ§å¼º
    -0.18
    عÙĪا
    -0.18
    ifetime
    -0.18
    POSITIVE LOGITS
     level
    0.34
     levels
    0.34
    -level
    0.32
    level
    0.32
    levels
    0.30
    ä¸įé«ĺ
    0.30
    è¶Ĭé«ĺ
    0.28
    /high
    0.28
    æ°´å¹³
    0.28
    é«ĺçļĦ
    0.27
    Activations Density 2.974%

    No Known Activations