© 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. 738
    Prev
    Next
    INDEX
    Explanations

    spatial relation

    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
     subrange
    -0.28
    LTRB
    -0.25
    CCCCCC
    -0.25
     Playoff
    -0.25
     removeObject
    -0.24
    webdriver
    -0.24
    ÃŃculo
    -0.24
    ðŁĻĤ
    -0.24
     perpetr
    -0.24
    èĪ¯
    -0.24
    POSITIVE LOGITS
    éĿ¢åIJij
    0.31
    侧éĿ¢
    0.28
     opposite
    0.28
    ä½įç½®
    0.27
     toward
    0.27
     towards
    0.25
     cigaret
    0.25
    äºĨè¿ĩæĿ¥
    0.25
     position
    0.25
    è¿ľç¦»
    0.25
    Activations Density 3.681%

    No Known Activations