© 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. 15267
    Prev
    Next
    INDEX
    Explanations

    policy domains

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

    No Comments

    Negative Logits
    .lambda
    -18.75
     lambda
    -18.63
     Lambda
    -18.25
    VES
    -18.13
    (lambda
    -18.13
    lambda
    -17.88
    rowse
    -17.63
    еля
    -17.25
    =lambda
    -17.00
    _SSL
    -16.75
    POSITIVE LOGITS
     freezing
    18.50
     Frozen
    17.00
    冷冻
    17.00
    基建
    17.00
     frozen
    16.38
    冻
    16.25
     thaw
    15.88
     froze
    15.50
    .freeze
    15.00
     tax
    14.56
    Activations Density 0.208%

    No Known Activations