© 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. 14411
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
    Mah
    -19.13
    .nih
    -18.50
     Rox
    -18.38
     Rah
    -18.25
     �
    -18.00
    萘
    -17.88
     Yorkshire
    -17.63
    邺
    -17.38
    Bah
    -17.25
    鸡汤
    -17.13
    POSITIVE LOGITS
    fsp
    18.63
    bsp
    18.13
     dart
    17.88
    dsp
    17.88
    dart
    17.88
    arty
    17.25
    崆
    17.25
    cq
    17.13
     squeezed
    17.13
     squeez
    17.13
    Activations Density 1.382%

    No Known Activations