© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14368
    Prev
    Next
    INDEX
    Explanations

    1 => 1

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

    No Comments

    Negative Logits
    ika
    -19.38
    umas
    -17.75
    orum
    -17.63
    ikal
    -17.38
     kHz
    -17.38
    tera
    -17.13
    lia
    -17.00
     Kear
    -16.75
    kal
    -16.63
    steen
    -16.50
    POSITIVE LOGITS
    阳
    18.00
    陽
    17.63
     Bent
    15.88
    Winter
    15.75
     Eng
    15.75
     Rect
    15.25
    揚
    15.13
    端午
    15.06
    冬
    14.94
    engu
    14.69
    Activations Density 0.037%

    No Known Activations