© 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. 14497
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
    onna
    -19.50
     zipper
    -17.63
    uppet
    -17.13
    orney
    -17.00
    离
    -16.38
    _insn
    -16.00
    出境
    -15.75
     pressure
    -15.69
    venge
    -15.69
    離
    -15.44
    POSITIVE LOGITS
    蝶
    14.69
    afil
    14.44
    idot
    14.25
     ByVal
    13.75
    Forgot
    13.38
     East
    13.31
    avad
    13.13
     bậc
    13.06
     Bik
    13.06
     Aer
    12.88
    Activations Density 0.879%

    No Known Activations