© 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. 1432
    Prev
    Next
    INDEX
    Explanations

    numbers and durations

    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
    .MaxValue
    -0.22
    /includes
    -0.22
    ;++
    -0.21
     ParseException
    -0.20
    .OrderByDescending
    -0.20
    @Table
    -0.20
    ukkit
    -0.20
    Ã¼ÄŁ
    -0.20
    åij¸
    -0.19
    Ã¼ÄŁÃ¼
    -0.18
    POSITIVE LOGITS
    æĹ¥èĩ³
    0.44
    èĩ³
    0.36
    æľĪèĩ³
    0.35
    å¹´èĩ³
    0.34
    å¼Ģå§ĭ
    0.30
     beginning
    0.27
     èĩ
    0.26
    ä¹ĭæĹ¥èµ·
    0.26
    @student
    0.25
     Cutter
    0.25
    Activations Density 1.500%

    No Known Activations