© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2328
    Prev
    Next
    INDEX
    Explanations

    say "ver" words

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

    No Comments

    Negative Logits
    [cur
    -24.88
     Reg
    -24.38
    (cur
    -23.63
    reg
    -23.50
     reg
    -23.50
     cur
    -23.13
     registry
    -23.13
    .cur
    -23.13
    -reg
    -23.00
    (reg
    -22.88
    POSITIVE LOGITS
     verbal
    41.25
     Ver
    35.25
     verbally
    33.50
    Ver
    31.88
    ver
    30.25
    Verb
    29.75
     Verb
    29.00
    (ver
    28.88
    .Ver
    27.88
    verb
    26.63
    Activations Density 0.092%

    No Known Activations