© 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. 14637
    Prev
    Next
    INDEX
    Explanations

    Irish war history

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

    No Comments

    Negative Logits
    loo
    -19.00
    quared
    -18.00
    Parcelable
    -17.75
    lain
    -17.25
     chai
    -17.00
    惕
    -16.88
    lea
    -16.75
    parity
    -16.75
    loom
    -16.63
    爱尔兰
    -16.50
    POSITIVE LOGITS
     Vanguard
    14.19
    的就是
    13.38
    -mounted
    13.38
    ->$
    13.31
    钦
    13.13
    监视
    12.88
    博览
    12.81
    swer
    12.50
    议事
    12.38
     plut
    12.00
    Activations Density 0.046%

    No Known Activations