© 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. 1142
    Prev
    Next
    INDEX
    Explanations

    known

    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
    ThanOrEqualTo
    -0.23
    ('{{
    -0.21
    æŃ£å¼ıåIJ¯åĬ¨
    -0.21
    ogenerated
    -0.21
    AdapterManager
    -0.20
    èIJĭ
    -0.20
    ropri
    -0.20
    }}],↵
    -0.19
    ampoo
    -0.19
    :NO
    -0.19
    POSITIVE LOGITS
    çİ°æľī
    0.27
    èĩ³ä»Ĭ
    0.26
     attempts
    0.26
    Attempts
    0.25
    解åĨ³æĸ¹æ¡Ī
    0.25
     known
    0.24
    <decltype
    0.24
    å°Ŀè¯ķ
    0.23
     SUMMARY
    0.23
    æѤ类
    0.23
    Activations Density 3.295%

    No Known Activations