© 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. 14902
    Prev
    Next
    INDEX
    Explanations

    proper nouns

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

    No Comments

    Negative Logits
    pesan
    -16.63
    lectual
    -16.63
    ulti
    -16.38
    ضار
    -16.13
    roys
    -16.13
     controlId
    -15.19
    olland
    -14.94
    roman
    -14.94
    ellij
    -14.81
    .getAs
    -14.81
    POSITIVE LOGITS
    ley
    14.63
     Phantom
    14.38
    puty
    13.56
     Millennium
    13.06
    仿真
    12.75
    .IS
    12.50
     Age
    12.44
     beck
    12.44
    asts
    12.25
    LEX
    12.25
    Activations Density 0.069%

    No Known Activations