© 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. 1031
    Prev
    Next
    INDEX
    Explanations

    math and scientific notation

    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
    .KeyPress
    -0.21
     Españ
    -0.21
    ].'
    -0.20
     LENG
    -0.20
    åµ´
    -0.20
    æ³ħ
    -0.20
    apor
    -0.20
     RIGHTS
    -0.20
    ').'
    -0.20
    è¿Ļ个èģĮä¸ļ
    -0.20
    POSITIVE LOGITS
    Äĩe
    0.23
     where
    0.20
    ombat
    0.20
    --;↵↵
    0.20
    Ã¤ÃŁig
    0.20
     :";↵
    0.20
    ätig
    0.20
    .addProperty
    0.19
    :".$
    0.19
    _".$
    0.19
    Activations Density 0.116%

    No Known Activations