© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 776
    Prev
    Next
    INDEX
    Explanations

    say Finnish conjunctions

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

    No Comments

    Negative Logits
    材料
    -17.00
    ibs
    -13.56
    ．
    -12.88
    bras
    -12.44
    潜水
    -12.19
     backpack
    -12.19
    cri
    -12.19
    惰
    -11.88
     obt
    -11.75
     material
    -11.69
    POSITIVE LOGITS
     ja
    26.88
     tai
    26.13
     ku
    22.13
     kir
    21.13
     sek
    20.88
     kim
    20.88
     ka
    20.75
     kun
    20.50
    .fi
    20.00
    ikk
    19.75
    Activations Density 0.032%

    No Known Activations