© 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. 450
    Prev
    Next
    INDEX
    Explanations

    non‑English words

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

    No Comments

    Negative Logits
     Sawyer
    -16.88
     Davies
    -15.63
    Henry
    -15.44
     Hyper
    -15.31
     Desmond
    -15.19
    詹姆斯
    -15.13
    Hyper
    -15.00
    (inter
    -14.94
     Carolyn
    -14.44
    (Cl
    -14.38
    POSITIVE LOGITS
     ku
    25.25
     kod
    23.50
     kol
    21.88
     ki
    21.25
     kun
    20.75
     kom
    20.75
     tek
    20.25
     kop
    20.25
     kam
    20.25
     tu
    20.25
    Activations Density 0.120%

    No Known Activations