© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15550
    Prev
    Next
    INDEX
    Explanations

    academic citations

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

    No Comments

    Negative Logits
    尼克
    -18.00
    �
    -17.38
    峪
    -17.13
    ランス
    -17.13
    龚
    -17.13
    奚
    -16.75
    仑
    -16.38
    LEX
    -15.81
    博物
    -15.44
    烟囱
    -15.44
    POSITIVE LOGITS
    (td
    38.25
     Cd
    35.25
    	td
    35.25
    (pd
    35.00
     cad
    35.00
     PD
    35.00
    ud
    34.50
    _pd
    34.00
    (ld
    33.50
     gd
    33.25
    Activations Density 7.043%

    No Known Activations