© 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. 572
    Prev
    Next
    INDEX
    Explanations

    say fish

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

    No Comments

    Negative Logits
     Tennessee
    -20.13
    antt
    -18.88
    芬兰
    -18.50
    爱尔兰
    -17.00
    WASHINGTON
    -16.75
     Nashville
    -16.75
    Egypt
    -16.50
    新西兰
    -16.38
     cabin
    -16.25
    乐器
    -16.25
    POSITIVE LOGITS
     Yoshi
    17.88
    舐
    17.00
     rab
    15.94
    ###↵↵
    15.56
    舔
    15.25
    鲨
    15.25
     Gut
    15.19
     Fish
    15.06
    池
    15.06
    钓鱼
    14.69
    Activations Density 0.077%

    No Known Activations