© 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. 15696
    Prev
    Next
    INDEX
    Explanations

    non‑ASCII characters

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

    No Comments

    Negative Logits
    acs
    -18.50
     drains
    -17.88
     cooldown
    -17.38
    ringe
    -17.38
    irts
    -17.25
     drain
    -17.13
    rels
    -17.13
     retarded
    -17.00
     discarded
    -16.88
    BITS
    -16.88
    POSITIVE LOGITS
    镭
    18.38
     Cub
    17.25
    生肖
    17.13
     gql
    17.00
     cub
    16.75
    楷
    16.25
    鹊
    16.00
    楠
    16.00
     cubic
    15.81
     Rider
    15.69
    Activations Density 1.105%

    No Known Activations