© 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. 2951
    Prev
    Next
    INDEX
    Explanations

    say "fort" words

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

    No Comments

    Negative Logits
     Med
    -21.38
     rel
    -20.88
    (rel
    -20.75
    Med
    -19.50
     cap
    -18.38
     med
    -18.13
     Rel
    -18.13
    Det
    -18.13
     Cap
    -18.00
     param
    -17.75
    POSITIVE LOGITS
    Fort
    34.75
     Fortune
    34.25
    fort
    32.25
     fortune
    31.50
     Fort
    30.25
    fortune
    30.13
     fort
    27.50
     fortunes
    21.13
     fortn
    19.50
     fortress
    19.38
    Activations Density 0.023%

    No Known Activations