© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2672
    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
    .isNullOrEmpty
    -0.23
     ucwords
    -0.23
    'icon
    -0.22
    ç¦ļ
    -0.21
    UILT
    -0.21
    	perror
    -0.20
    ä»ī
    -0.20
    'options
    -0.20
    		    ↵
    -0.20
    loquent
    -0.20
    POSITIVE LOGITS
    ActivityIndicator
    0.21
    æĤł
    0.21
    ácil
    0.19
    мÑĭÑģл
    0.19
    webdriver
    0.19
    ése
    0.18
    _##
    0.18
    å°º
    0.18
     Nelson
    0.18
     modelAndView
    0.18
    Activations Density 0.001%

    No Known Activations