© 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. 2710
    Prev
    Next
    INDEX
    Explanations

    间

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

    No Comments

    Negative Logits
     Meg
    -18.13
    .ev
    -17.88
     terr
    -17.50
     regress
    -16.63
     TEM
    -16.50
    hex
    -16.50
    道德
    -16.38
     empir
    -16.00
     percent
    -15.81
    (percent
    -15.75
    POSITIVE LOGITS
     Meth
    20.38
    sem
    17.38
    Perm
    16.88
     sem
    16.25
     semi
    15.94
    Sem
    15.81
    ero
    15.81
    ERO
    15.50
    (gen
    15.44
     meth
    15.38
    Activations Density 0.067%

    No Known Activations