© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 826
    Prev
    Next
    INDEX
    Explanations

    historical figures

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

    No Comments

    Negative Logits
    芷
    -19.25
    (rt
    -18.13
     Rc
    -17.88
    gi
    -17.75
    乂
    -17.63
     rt
    -17.50
     Qi
    -17.00
     Ki
    -17.00
    ,tp
    -16.50
     cps
    -16.38
    POSITIVE LOGITS
    WF
    26.13
    BF
    23.88
     WF
    21.13
     SF
    20.75
    SF
    20.75
     BF
    20.63
     BN
    20.63
    WG
    19.88
    ML
    19.75
    MF
    19.75
    Activations Density 0.180%

    No Known Activations