© 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. 2304
    Prev
    Next
    INDEX
    Explanations

    any / whatever

    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
    ábado
    -0.21
     },↵↵↵
    -0.20
    SingleOrDefault
    -0.19
    exels
    -0.19
     cáºŃn
    -0.19
     guarante
    -0.19
    cks
    -0.19
     ApplicationContext
    -0.19
    hasOne
    -0.18
    [sizeof
    -0.18
    POSITIVE LOGITS
    ä»»ä½ķ
    0.60
     any
    0.56
    ä»»æĦı
    0.51
    any
    0.48
    ä»»ä½ķæŶåĢĻ
    0.47
    åıªè¦ģæĺ¯
    0.46
     whatever
    0.46
    ä»»ä½ķä¸Ģ个
    0.45
    ä»»ä½ķå½¢å¼ı
    0.45
     cualquier
    0.44
    Activations Density 0.656%

    No Known Activations