© 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. 15019
    Prev
    Next
    INDEX
    Explanations

    say 9

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

    No Comments

    Negative Logits
    normalize
    -16.38
    iples
    -16.13
    mailbox
    -16.00
    emarks
    -15.63
    mark
    -15.50
    iac
    -15.44
    endas
    -15.06
    hammer
    -14.75
    exc
    -14.69
    ighted
    -14.56
    POSITIVE LOGITS
     Gel
    18.13
    ogl
    17.75
    .gl
    16.63
    橄榄
    16.38
     glued
    16.25
    珊
    16.13
    咨
    15.69
    pré
    15.44
     gel
    15.44
     gl
    15.31
    Activations Density 0.051%

    No Known Activations