© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15460
    Prev
    Next
    INDEX
    Explanations

    century terms

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

    No Comments

    Negative Logits
     Ł
    -15.38
    Assembler
    -14.81
    alsy
    -14.69
    �
    -14.63
    配料
    -14.25
    判处
    -14.19
    泄
    -14.13
    校外
    -14.00
    篮
    -13.94
    Components
    -13.81
    POSITIVE LOGITS
    eenth
    25.13
    十九
    19.88
     век
    19.63
     ninete
    19.25
    十八
    18.75
    teenth
    18.25
    时代
    18.25
    rei
    18.13
     age
    18.00
    cent
    17.63
    Activations Density 0.226%

    No Known Activations