© 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. 1359
    Prev
    Next
    INDEX
    Explanations

    say "w" words

    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
    ].'
    -0.26
    iams
    -0.22
    :".$
    -0.22
    RIA
    -0.22
    ').'
    -0.22
    !=(
    -0.21
    Ī
    -0.20
    ilmington
    -0.20
    ificate
    -0.20
     ?>↵↵↵
    -0.20
    POSITIVE LOGITS
    anzi
    0.21
    ä¼IJ
    0.19
     AsyncStorage
    0.18
    ajaran
    0.18
    .tim
    0.18
    æħ¢
    0.18
     Publié
    0.18
    ç»Ļ大家
    0.18
    ä¸Ģè§Ī
    0.18
    忽
    0.17
    Activations Density 0.001%

    No Known Activations