© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 489
    Prev
    Next
    INDEX
    Explanations

    say tech companies

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

    No Comments

    Negative Logits
    莒
    -21.00
     Mali
    -20.38
     Algeria
    -19.38
     Angola
    -19.13
     roma
    -19.13
     Provincial
    -18.88
    邾
    -18.88
     Romania
    -18.88
     Ankara
    -18.50
    鄱
    -18.50
    POSITIVE LOGITS
    硅谷
    38.25
    英特尔
    34.50
    IBM
    34.25
     IBM
    32.75
    微软
    29.25
    哈佛
    29.25
     Silicon
    29.13
     Apple
    28.75
    华尔街
    28.63
     Stanford
    27.75
    Activations Density 0.601%

    No Known Activations