© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 995
    Prev
    Next
    INDEX
    Explanations

    say video

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

    No Comments

    Negative Logits
     rh
    -21.00
    Solar
    -19.25
    蚯
    -18.25
     collateral
    -17.88
    太阳能
    -17.75
    土壤
    -17.63
    礁
    -17.50
     solar
    -17.50
    washer
    -17.38
     planting
    -17.25
    POSITIVE LOGITS
    播放
    34.25
     video
    33.50
    视频
    33.25
     Video
    32.50
    Video
    30.63
     MPEG
    30.63
    .Video
    30.38
    video
    30.25
    (video
    30.25
    	video
    30.00
    Activations Density 0.168%

    No Known Activations