© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 566
    Prev
    Next
    INDEX
    Explanations

    specific terms

    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
     beneficiation
    -0.24
    ysqli
    -0.23
    #Region
    -0.22
     Dabei
    -0.20
    åĬĽè¿ĺæĺ¯
    -0.20
    åĹ³
    -0.20
    ($(".
    -0.20
    ESSAGE
    -0.20
    dorf
    -0.20
    classed
    -0.20
    POSITIVE LOGITS
    toPromise
    0.20
    Craft
    0.20
    åĻĺ
    0.19
    âĦī
    0.19
     capÃŃtulo
    0.18
     ún
    0.18
    é³Ķ
    0.18
    黥
    0.18
    -awesome
    0.18
    åĽ½éĻħåľ¨çº¿
    0.17
    Activations Density 0.012%

    No Known Activations