© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14558
    Prev
    Next
    INDEX
    Explanations

    say 9

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

    No Comments

    Negative Logits
     grill
    -20.88
     Chapel
    -19.13
     pupil
    -17.25
     Grill
    -17.00
     dile
    -17.00
     consoles
    -16.75
     Michele
    -16.63
    频道
    -16.25
    菜鸟
    -16.13
    寝室
    -16.00
    POSITIVE LOGITS
    七个
    21.00
    ７
    19.13
    asher
    19.13
     seventeen
    18.75
     seventh
    18.63
    .sa
    18.38
     Bangladesh
    18.38
    (rd
    18.13
     seven
    17.75
    第七
    17.75
    Activations Density 0.040%

    No Known Activations