© 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. 1726
    Prev
    Next
    INDEX
    Explanations

    method function

    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
    æķŀ
    -0.22
    åijĸ
    -0.21
    -UA
    -0.20
    edback
    -0.20
    ()){
    -0.20
    searchModel
    -0.19
    æĿIJè´¨
    -0.19
    æ¹İ
    -0.19
     material
    -0.18
    æĸĻ
    -0.18
    POSITIVE LOGITS
     function
    0.45
    åĩ½æķ°
    0.42
    function
    0.38
     functions
    0.35
     Function
    0.34
     íķ¨ìĪĺ
    0.34
     func
    0.34
    Function
    0.33
    -function
    0.31
    _function
    0.30
    Activations Density 2.867%

    No Known Activations