© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 988
    Prev
    Next
    INDEX
    Explanations

    say w

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

    No Comments

    Negative Logits
    莓
    -15.69
     FirebaseFirestore
    -14.75
    eren
    -14.63
    avax
    -14.56
    ptom
    -14.50
     Salvador
    -14.38
     Pied
    -14.38
     Finch
    -14.00
    蕺
    -13.56
    娄
    -13.44
    POSITIVE LOGITS
     WS
    60.75
     WA
    57.00
    WS
    56.25
     WB
    55.25
     WP
    54.75
     WC
    54.25
     WD
    53.00
     UW
    52.75
     WM
    52.75
     PW
    51.75
    Activations Density 1.403%

    No Known Activations