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

    Neuronpedia

    Jacobian LensNEW
    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. 15283
    Prev
    Next
    INDEX
    Explanations

    say "8"

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

    No Comments

    Negative Logits
     Salman
    -23.75
     Sachs
    -22.88
     solder
    -21.88
     Simpson
    -20.63
     Salmon
    -20.38
     Tiger
    -20.25
     Sawyer
    -20.13
    gamma
    -20.00
     Sage
    -19.50
     scooter
    -19.13
    POSITIVE LOGITS
    quina
    16.50
    EFR
    15.94
    indr
    15.88
    邝
    15.63
     créd
    15.63
    痘
    15.00
     Anita
    14.88
    男主
    14.63
    probe
    14.50
    inux
    14.13
    Activations Density 0.106%

    No Known Activations