© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2087
    Prev
    Next
    INDEX
    Explanations

    say membrane

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

    No Comments

    Negative Logits
    -Cs
    -14.88
    publisher
    -14.63
    .pkg
    -14.06
     Cumberland
    -14.00
     helicopters
    -13.88
    balls
    -13.69
    条评论
    -13.38
    ма
    -13.25
    直升机
    -13.19
    _WORDS
    -13.13
    POSITIVE LOGITS
     Mem
    86.50
    膜
    86.50
     membrane
    83.00
    Mem
    81.00
    (mem
    80.00
    mem
    78.00
     mem
    78.00
    	mem
    77.50
     membranes
    76.50
    _mem
    72.50
    Activations Density 0.085%

    No Known Activations