© 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. 992
    Prev
    Next
    INDEX
    Explanations

    scientific/academic 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
    /bower
    -0.22
    auważ
    -0.22
    .AutoComplete
    -0.21
    ivant
    -0.21
     AssemblyVersion
    -0.21
    ieten
    -0.21
    çļĦ带é¢Ĩ
    -0.20
    éĵĮ
    -0.19
    主ä¹īæĢĿæĥ³
    -0.19
    导è´Ń
    -0.19
    POSITIVE LOGITS
    ĴĮ
    0.21
    esor
    0.20
    SED
    0.19
    æ¾Į
    0.19
    nda
    0.18
    éĢī
    0.18
    isha
    0.18
    antor
    0.18
     Rudd
    0.17
     flexGrow
    0.17
    Activations Density 0.001%

    No Known Activations