© 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. 1252
    Prev
    Next
    INDEX
    Explanations

    relative pronouns

    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
    对çħ§æ£ĢæŁ¥
    -0.30
    berra
    -0.29
    çݩ家æĿ¥è¯´
    -0.28
    *****č↵
    -0.28
    rics
    -0.27
     Åļw
    -0.26
     --------------------------------------------------------------------------↵
    -0.25
    ].'
    -0.24
    ä»İ严治
    -0.24
    /↵↵↵↵
    -0.24
    POSITIVE LOGITS
     that
    0.57
     whose
    0.57
     which
    0.48
    that
    0.48
    whose
    0.46
    which
    0.39
     who
    0.33
    	that
    0.32
     коÑĤоÑĢÑĭй
    0.31
     wich
    0.31
    Activations Density 8.076%

    No Known Activations