© 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. 14979
    Prev
    Next
    INDEX
    Explanations

    say stone

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

    No Comments

    Negative Logits
    bsp
    -20.50
    mpr
    -17.63
    EmailAddress
    -17.38
    网购
    -17.38
    bonus
    -17.25
    refund
    -16.75
    _DSP
    -16.50
     Bonus
    -16.38
    udu
    -16.25
    /ws
    -16.00
    POSITIVE LOGITS
    石
    52.25
     stone
    49.25
    石头
    47.25
     stones
    45.25
     Stone
    44.75
     rock
    44.75
    岩石
    44.25
     Rock
    44.00
     rocks
    43.75
    stone
    41.25
    Activations Density 0.079%

    No Known Activations