© 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. 15654
    Prev
    Next
    INDEX
    Explanations

    say "t"

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

    No Comments

    Negative Logits
    箫
    -22.38
    骊
    -19.50
    峄
    -19.13
    驺
    -19.00
    崂
    -18.88
    岜
    -18.75
    珩
    -18.75
    淮
    -18.38
    阆
    -18.00
    金陵
    -17.88
    POSITIVE LOGITS
    JT
    33.25
     QT
    33.25
     JT
    32.75
    (bt
    32.50
    (ht
    32.50
     HT
    32.25
    HT
    32.00
    VT
    31.75
     VT
    30.75
    bt
    30.63
    Activations Density 6.972%

    No Known Activations