© 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. 1172
    Prev
    Next
    INDEX
    Explanations

    technical 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
    游æĪıæĵįä½ľ
    -0.24
    åħļæĢ»
    -0.24
     },{
    -0.21
    :';↵
    -0.20
    ey
    -0.20
    åķ»
    -0.20
    \:
    -0.20
     ';↵↵
    -0.19
    ')?></
    -0.19
    æĽĻ
    -0.19
    POSITIVE LOGITS
    regunta
    0.24
     (![
    0.23
    åĿļå®ļä¸į
    0.22
    atever
    0.22
    å®ŀäºĭæ±Ĥ
    0.21
    èĥ½åĬĽå¼º
    0.20
    (QObject
    0.20
    róż
    0.19
    è¦ģä¸įçĦ¶
    0.19
    以人æ°ij为
    0.19
    Activations Density 0.001%

    No Known Activations