© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15343
    Prev
    Next
    INDEX
    Explanations

    mountain climbing

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

    No Comments

    Negative Logits
    马云
    -17.63
    }while
    -16.88
    cats
    -16.75
    holds
    -16.63
    icl
    -16.50
    ABL
    -16.50
    𝑴
    -16.38
    İM
    -16.25
    ensible
    -16.13
    PRESSION
    -16.00
    POSITIVE LOGITS
    icer
    14.75
    .Library
    14.38
     Pratt
    14.13
    bro
    13.69
     liber
    13.63
    Lib
    13.19
    自愿
    13.06
     adm
    12.88
     Liberty
    12.81
     lib
    12.50
    Activations Density 0.070%

    No Known Activations