© 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. 2514
    Prev
    Next
    INDEX
    Explanations

    discounts and offers

    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
    .isRequired
    -0.22
    æĶ¶è´¹
    -0.22
     há»ĵ
    -0.21
    (strpos
    -0.20
    伸ãģ³
    -0.20
    å¼Ģå¥ĸç»ĵæŀľ
    -0.20
    éĶĢ
    -0.19
    BASH
    -0.19
    	namespace
    -0.19
    åĶ®ç¥¨
    -0.19
    POSITIVE LOGITS
    roupon
    0.27
    undai
    0.27
    vertiser
    0.26
    ocard
    0.22
    _bundle
    0.22
    gars
    0.22
    (ErrorMessage
    0.21
    detalle
    0.21
    Disposition
    0.21
     deal
    0.20
    Activations Density 0.364%

    No Known Activations