© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14611
    Prev
    Next
    INDEX
    Explanations

    say "verb tags"

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

    No Comments

    Negative Logits
    Rio
    -19.13
    abbo
    -18.75
     reck
    -17.63
    rice
    -17.63
     rac
    -17.63
    bose
    -17.63
     radiation
    -17.50
    inson
    -17.38
     resc
    -17.25
    قا
    -17.25
    POSITIVE LOGITS
    VP
    17.88
     vp
    17.50
    plit
    17.38
    _vp
    17.00
     Hop
    16.88
     Bret
    16.75
    vit
    16.63
     Holt
    16.63
    VT
    16.63
    het
    16.63
    Activations Density 0.621%

    No Known Activations