© 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. 15049
    Prev
    Next
    INDEX
    Explanations

    say left bracket

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

    No Comments

    Negative Logits
    sar
    -18.75
    (pol
    -18.63
     Pandora
    -18.63
     Henrik
    -18.50
     Suzuki
    -18.25
    戟
    -17.50
    (pm
    -17.38
     Cyr
    -17.25
    امة
    -16.75
     Pike
    -16.63
    POSITIVE LOGITS
    [
    20.88
    [x
    18.63
    [d
    18.13
    [#
    18.00
    [\
    17.13
    [--
    17.00
    [X
    17.00
    [*
    16.88
    [len
    16.88
    [num
    16.88
    Activations Density 0.021%

    No Known Activations