© 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. 14960
    Prev
    Next
    INDEX
    Explanations

    嘟

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

    No Comments

    Negative Logits
    bare
    -21.38
    aret
    -20.63
     Kirk
    -18.88
    sitemap
    -18.63
     arb
    -18.38
     Pare
    -18.38
    arem
    -18.38
    炜
    -18.25
     Warren
    -18.13
    (AdapterView
    -18.13
    POSITIVE LOGITS
    alsa
    25.88
    黑龙
    23.25
    pls
    19.50
    fce
    19.38
     Johnson
    19.00
     AHL
    18.88
     cycl
    18.75
    捕捉
    18.75
     MLS
    18.75
    永利
    18.63
    Activations Density 1.148%

    No Known Activations