© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4380
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    Negative Logits
    =Value
    -0.27
    ');↵↵↵↵
    -0.26
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.26
    ÑĩÑĥв
    -0.25
    ',...↵
    -0.24
    ,eg
    -0.24
    uxtap
    -0.23
    )))),
    -0.23
    ');//
    -0.23
     (*((
    -0.23
    POSITIVE LOGITS
    zburg
    0.23
    é»Ħ
    0.19
     right
    0.19
     DispatchQueue
    0.19
    _FRONT
    0.19
     scal
    0.19
    èĩªçĦ¶
    0.19
    åİŁæĸĩåľ°åĿĢ
    0.18
     clearColor
    0.18
     resultMap
    0.18
    Activations Density 0.010%

    No Known Activations