© 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. 1956
    Prev
    Next
    INDEX
    Explanations

    code and headers

    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
    akest
    -0.30
    ,assign
    -0.24
    .AI
    -0.24
    UGC
    -0.23
    europ
    -0.23
    æĿ¨æ¬¢
    -0.22
    åıµ
    -0.22
    xes
    -0.22
    rena
    -0.22
    écran
    -0.22
    POSITIVE LOGITS
    	UP
    0.24
    åİŁæĸĩåľ°åĿĢ
    0.23
    个å¤ļ
    0.22
    社ä¼ļåĮĸ
    0.22
     dak
    0.22
    .downcase
    0.21
    ='{$
    0.21
    çļĦ带é¢Ĩ
    0.21
    ยว
    0.21
    åij¸
    0.20
    Activations Density 0.629%

    No Known Activations