© 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. 14722
    Prev
    Next
    INDEX
    Explanations

    [juice] => [fruit]

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

    No Comments

    Negative Logits
    樱桃
    -19.25
    agas
    -18.50
    _checkout
    -17.50
    oku
    -17.38
    berry
    -17.00
    spiel
    -16.63
    _android
    -16.63
    ableView
    -16.50
    采摘
    -16.50
     cocoa
    -16.38
    POSITIVE LOGITS
     Kra
    14.63
    -imm
    14.44
    -rel
    13.31
    rel
    13.19
     Rel
    13.19
    zym
    13.00
    澜
    12.94
    胁
    12.44
     Gre
    12.31
    .Table
    11.94
    Activations Density 0.050%

    No Known Activations