© 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. 14891
    Prev
    Next
    INDEX
    Explanations

    [name] => D

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

    No Comments

    Negative Logits
    CTR
    -17.88
    MIC
    -17.75
    mv
    -16.88
    胡
    -16.88
    .arm
    -16.38
    猕
    -16.38
    mü
    -16.38
     arms
    -15.94
     ExecutionContext
    -15.81
    候
    -15.69
    POSITIVE LOGITS
    DataSetChanged
    16.75
    chap
    16.38
    ades
    16.25
     sap
    16.00
    opo
    15.50
    atal
    14.19
    麻木
    14.13
    aches
    14.06
     ch
    13.69
     pain
    13.44
    Activations Density 0.006%

    No Known Activations