© 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. 15736
    Prev
    Next
    INDEX
    Explanations

    say foreign characters

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

    No Comments

    Negative Logits
    -t
    -46.50
    -T
    -40.50
    	td
    -39.00
    _t
    -38.75
    +t
    -38.50
    =t
    -38.25
    泰
    -37.75
    -te
    -37.50
    _ta
    -37.25
    /t
    -37.00
    POSITIVE LOGITS
    heits
    14.00
    椅子
    12.88
    phan
    12.88
     Wedding
    12.75
    思い出
    12.50
    okit
    12.38
    kır
    12.31
    emet
    12.25
    phet
    12.25
     Orlando
    12.13
    Activations Density 3.344%

    No Known Activations