© 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. 30
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

    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
     fillColor
    -0.21
     =>'
    -0.21
    æ³£
    -0.20
     setBackground
    -0.20
     gameObject
    -0.20
     ifdef
    -0.19
    é½IJåħ¨
    -0.19
     congr
    -0.19
    ãģij
    -0.19
    éģµ
    -0.19
    POSITIVE LOGITS
    /Dk
    0.30
    è¸Ķ
    0.28
    elerik
    0.27
     embod
    0.26
    @dynamic
    0.26
    velte
    0.25
     nuest
    0.25
    DMETHOD
    0.24
    /WebAPI
    0.23
    黧
    0.23
    Activations Density 0.326%

    No Known Activations