© 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. 14896
    Prev
    Next
    INDEX
    Explanations

    say a

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

    No Comments

    Negative Logits
     washer
    -18.75
    EA
    -18.63
    ertext
    -18.25
    pee
    -18.13
    pio
    -17.50
    闱
    -17.50
    ガイ
    -17.25
     Epstein
    -17.13
     Moran
    -17.13
     sausage
    -17.00
    POSITIVE LOGITS
    c
    14.44
     ung
    13.75
     Cros
    13.50
    @c
    12.50
    ibre
    12.50
     c
    12.38
    لك
    12.31
    ustum
    12.13
     Cu
    12.00
    导
    12.00
    Activations Density 0.002%

    No Known Activations