© 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. 15552
    Prev
    Next
    INDEX
    Explanations

    say "→"

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

    No Comments

    Negative Logits
     Colo
    -19.00
    萩
    -18.25
    ╭
    -18.13
    -Col
    -18.00
     Colonial
    -17.88
     PSP
    -17.25
     PSA
    -17.25
     colonial
    -17.25
    ergus
    -17.13
    (att
    -16.88
    POSITIVE LOGITS
    1
    16.63
    xic
    16.38
    幸
    14.94
     dictionary
    14.38
    Tree
    14.13
     Costco
    14.13
     Dick
    14.00
    �
    13.75
    Dic
    13.69
     McMahon
    13.50
    Activations Density 0.090%

    No Known Activations