© 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. 15469
    Prev
    Next
    INDEX
    Explanations

    [name] => [surname]

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

    No Comments

    Negative Logits
    笮
    -15.13
    蛸
    -13.81
    acock
    -13.38
    戢
    -13.13
    芜
    -13.06
    栊
    -13.06
    绿豆
    -12.81
     Pierce
    -12.75
    .LookAndFeel
    -12.63
    ką
    -12.63
    POSITIVE LOGITS
    -h
    50.00
    	hs
    45.50
    -H
    45.00
    hx
    44.50
    HA
    44.00
    HC
    43.50
    HB
    43.50
    HO
    43.00
    _h
    42.75
    /h
    42.75
    Activations Density 7.565%

    No Known Activations