© 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
    2. Qwen2.5-7B-IT
    3. 20-MATRYOSHKA-65K
    4. 3644
    Prev
    Next
    INDEX
    Explanations

    lists and references

    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
    èµĢ
    -0.21
     Ayrıca
    -0.19
    è®¤çľŁåŃ¦ä¹ł
    -0.19
    Insensitive
    -0.18
     "***
    -0.18
    ãĥ¶
    -0.17
    uur
    -0.17
    oss
    -0.17
    mouseleave
    -0.17
     pestic
    -0.17
    POSITIVE LOGITS
    $_['
    0.26
    lève
    0.22
     âĢ¢
    0.21
     madrid
    0.21
    ļĮ
    0.20
    /AFP
    0.20
     AndAlso
    0.20
    âĢ¢
    0.20
    >window
    0.20
    é³ķ
    0.20
    Activations Density 0.352%

    No Known Activations