© 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. 14415
    Prev
    Next
    INDEX
    Explanations

    say "0"

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

    No Comments

    Negative Logits
    榄
    -18.75
    ilver
    -16.75
     gag
    -15.88
    aver
    -15.19
    救人
    -15.06
    粱
    -14.88
     verw
    -14.75
    vern
    -14.56
    AndView
    -14.50
    ventions
    -14.44
    POSITIVE LOGITS
    .Euler
    16.50
     HC
    15.94
    urd
    15.94
    /e
    15.50
     euler
    15.31
    /E
    15.25
    HC
    15.13
    xdc
    15.06
    oustic
    15.00
    ads
    14.88
    Activations Density 0.008%

    No Known Activations