© 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. 14787
    Prev
    Next
    INDEX
    Explanations

    opening book quote

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

    No Comments

    Negative Logits
    ulos
    -18.75
    ős
    -17.75
    colon
    -17.50
    .MustCompile
    -15.81
    met
    -15.75
    stan
    -15.63
    storm
    -15.56
     settlements
    -15.44
    strom
    -15.25
     adress
    -15.25
    POSITIVE LOGITS
    رب
    14.06
    妫
    13.50
    aign
    13.44
    atri
    13.38
    心
    13.31
    kg
    13.25
    ypass
    13.00
    大力
    12.75
    /pg
    12.63
    提速
    12.63
    Activations Density 0.020%

    No Known Activations