© 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. 2096
    Prev
    Next
    INDEX
    Explanations

    prevalence frequency rate

    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
    eous
    -0.22
    æľį
    -0.21
    *)((
    -0.20
    é£Łãģ¹ãģ¦
    -0.20
     ''){↵
    -0.20
    ]init
    -0.20
    inoa
    -0.20
    |array
    -0.19
    .parseInt
    -0.19
     Erectile
    -0.19
    POSITIVE LOGITS
    çİĩ
    0.42
    æ¯Ķä¾ĭ
    0.41
    çİĩ为
    0.41
     prevalence
    0.40
     frequency
    0.40
    é¢ijçİĩ
    0.38
     Frequency
    0.35
     rate
    0.34
    çļĦæ¯Ķä¾ĭ
    0.33
    åıijçĹħçİĩ
    0.33
    Activations Density 0.762%

    No Known Activations