© 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. 244
    Prev
    Next
    INDEX
    Explanations

    data markers

    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
    	synchronized
    -0.22
    stdarg
    -0.22
    SSION
    -0.22
    åijĶ
    -0.22
    çķ¸
    -0.20
    ('/:
    -0.19
     "','
    -0.19
    æĭ©
    -0.19
    .tencent
    -0.19
    å©´
    -0.18
    POSITIVE LOGITS
    .epam
    0.33
    ".↵↵↵↵
    0.30
    ?"↵↵↵↵
    0.28
     (%)
    0.28
    .Today
    0.27
    :";č↵
    0.24
    ].'
    0.23
     francaise
    0.23
    :)↵
    0.23
    å¤ĩ注
    0.23
    Activations Density 0.327%

    No Known Activations