© 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. 15175
    Prev
    Next
    INDEX
    Explanations

    oscillation

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

    No Comments

    Negative Logits
     skype
    -14.94
     libertine
    -14.81
     ais
    -14.56
    rô
    -14.38
    heits
    -14.13
     Worce
    -14.06
     nudity
    -13.94
     responseBody
    -13.88
     (_.
    -13.81
     hoodie
    -13.75
    POSITIVE LOGITS
    .
    16.13
    、
    16.13
     
    16.13
    D
    15.88
    2
    15.81
    的
    15.63
    1
    15.56
    ed
    15.38
    ,
    15.25
    15.00
    Activations Density 0.369%

    No Known Activations