© 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. 2518
    Prev
    Next
    INDEX
    Explanations

    say 简

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

    No Comments

    Negative Logits
    (mut
    -22.75
     Mur
    -22.38
     Mut
    -21.25
     erm
    -20.88
     Er
    -19.13
     mut
    -18.75
     MUT
    -18.50
    mut
    -17.88
    _er
    -17.88
    mutations
    -17.38
    POSITIVE LOGITS
     Sim
    42.00
     sim
    41.50
    Sim
    40.75
    sim
    39.75
     SIM
    39.50
    简
    38.25
     sims
    37.50
    (sim
    37.00
    .sim
    36.75
    _sim
    36.25
    Activations Density 0.055%

    No Known Activations