© 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. 1022
    Prev
    Next
    INDEX
    Explanations

    say philosophers

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

    No Comments

    Negative Logits
    烟花爆竹
    -20.25
     acupuncture
    -19.25
     Tian
    -19.00
     Korea
    -18.38
     dental
    -18.13
     yuan
    -18.00
     Leafs
    -17.88
     Hong
    -17.88
     vape
    -17.75
     pension
    -17.63
    POSITIVE LOGITS
    柏
    17.38
    哲学
    16.75
    米尔
    15.88
    威廉
    15.00
     philosophers
    15.00
    时间和
    14.69
    柏林
    14.63
    伊斯
    14.56
    菲
    14.44
    德国
    14.44
    Activations Density 0.425%

    No Known Activations