© 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. 734
    Prev
    Next
    INDEX
    Explanations

    political parties

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

    No Comments

    Negative Logits
    Disk
    -18.50
     Webcam
    -18.25
     Licence
    -17.25
     RAF
    -17.00
     SAS
    -16.63
    相机
    -16.13
     cams
    -16.00
    (Properties
    -15.94
    disk
    -15.81
     Sussex
    -15.75
    POSITIVE LOGITS
     Hu
    21.63
    Hu
    19.25
     Chu
    17.38
     nominations
    17.25
     party
    17.00
     Duterte
    16.75
     Wu
    16.50
     Uzbek
    16.50
     Nicar
    16.38
    川
    16.38
    Activations Density 0.153%

    No Known Activations