© 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. 14762
    Prev
    Next
    INDEX
    Explanations

    [number] => 0

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

    No Comments

    Negative Logits
    ewan
    -19.38
    蔗
    -18.88
    #w
    -17.88
    iw
    -17.75
     weed
    -17.63
    苋
    -17.63
    tps
    -17.50
    -w
    -17.38
    &w
    -17.25
    ISC
    -17.00
    POSITIVE LOGITS
    浆
    18.75
    primer
    17.00
    BST
    16.00
     Belmont
    15.63
    Brun
    15.25
    bum
    15.06
    HUD
    15.06
     drum
    15.00
     bur
    14.88
    itori
    14.50
    Activations Density 0.080%

    No Known Activations