© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 863
    Prev
    Next
    INDEX
    Explanations

    say Devanagari

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

    No Comments

    Negative Logits
    天府
    -22.50
    成都市
    -20.88
    泸州
    -20.38
    川
    -20.00
    四川
    -19.88
    四川省
    -19.38
    成都
    -18.63
    阿根廷
    -18.13
     Los
    -18.00
     San
    -17.63
    POSITIVE LOGITS
     Ko
    23.00
     Ka
    21.00
    xdf
    20.75
     Ef
    20.75
    Ka
    20.50
     Cd
    20.13
    Cd
    19.63
    KK
    19.63
     EF
    19.50
     EE
    18.88
    Activations Density 0.014%

    No Known Activations

    This feature has no known activations.