© 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. 14693
    Prev
    Next
    INDEX
    Explanations

    8

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

    No Comments

    Negative Logits
    SOR
    -19.25
    jsp
    -18.25
     Bundy
    -18.00
    jet
    -17.25
    డ
    -16.63
    皇冠
    -16.50
    Juan
    -16.38
    elan
    -16.38
    aña
    -16.00
    荚
    -15.88
    POSITIVE LOGITS
    gorithm
    15.44
    ić
    14.50
    Mich
    14.44
    ych
    14.06
    に行って
    13.75
    iği
    13.50
    i
    13.19
    Algorithm
    13.13
    mag
    13.00
    에너지
    12.88
    Activations Density 0.085%

    No Known Activations