© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14927
    Prev
    Next
    INDEX
    Explanations

    say 0

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

    No Comments

    Negative Logits
    .Gr
    -18.38
    ogr
    -18.13
     grunt
    -17.50
     Drake
    -17.13
    eway
    -16.75
    agini
    -16.25
    edException
    -16.13
     dụng
    -16.13
     arreglo
    -15.94
    婺
    -15.63
    POSITIVE LOGITS
    煦
    17.38
    .eu
    17.38
    Sher
    17.13
    杲
    16.00
    曉
    15.94
    cea
    15.19
     Sok
    15.13
    晓
    14.88
    alls
    14.81
    bara
    14.81
    Activations Density 0.005%

    No Known Activations