© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 60
    Prev
    Next
    INDEX
    Explanations

    say "capitalized words"

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

    No Comments

    Negative Logits
    odu
    -19.38
    .pc
    -19.13
     pc
    -18.63
    StackSize
    -18.38
    pcs
    -17.63
    pc
    -17.63
    赣
    -17.00
    IPAddress
    -16.88
     usb
    -16.75
     Ow
    -16.75
    POSITIVE LOGITS
     VA
    17.13
     Elena
    17.00
     Kremlin
    16.63
    Psi
    16.63
     Natasha
    15.81
     QE
    15.69
     neuro
    15.44
     Afghan
    15.44
    toolbox
    15.06
    ring
    14.81
    Activations Density 0.243%

    No Known Activations