© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15816
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
    .ph
    -22.00
    quarters
    -20.25
    /php
    -20.00
    _PHP
    -19.88
     Quarter
    -19.75
    quí
    -19.38
    qm
    -19.38
    php
    -19.25
    quine
    -19.25
    PH
    -19.00
    POSITIVE LOGITS
    riel
    19.63
    lius
    18.38
    �
    18.25
     fringe
    18.13
     conspiracy
    17.50
    寰
    17.50
    枢
    17.25
     Citadel
    17.13
     lia
    16.50
    抟
    16.50
    Activations Density 0.732%

    No Known Activations