© 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. 1004
    Prev
    Next
    INDEX
    Explanations

    web page snippets

    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
    	Copyright
    -0.23
    onestly
    -0.22
    VERRIDE
    -0.22
    ãħł
    -0.21
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.20
    efeller
    -0.20
    .DataAnnotations
    -0.20
    <typeof
    -0.19
    :numel
    -0.19
     Ấ
    -0.19
    POSITIVE LOGITS
    jom
    0.21
     piger
    0.19
     nonatomic
    0.19
    ËĤ
    0.19
     novitÃł
    0.19
    usercontent
    0.19
    iane
    0.18
    ayas
    0.18
     Hits
    0.18
    åıįèħIJåĢ¡å»ī
    0.18
    Activations Density 2.139%

    No Known Activations