© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 569
    Prev
    Next
    INDEX
    Explanations

    Hadith citations

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .bukkit
    -17.00
     Fayette
    -15.63
    桐
    -15.31
    兵器
    -14.94
    苗木
    -14.63
     Scarlet
    -14.63
    agenta
    -14.38
    プレー
    -14.38
    ymbol
    -14.31
    ered
    -14.31
    POSITIVE LOGITS
    ống
    18.00
    	cv
    17.63
    南海
    17.50
    睡眠
    16.75
     orally
    16.75
    .coll
    16.63
     Oral
    16.63
    кли
    16.25
     Zucker
    16.25
    .library
    16.25
    Activations Density 0.046%

    No Known Activations