© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15456
    Prev
    Next
    INDEX
    Explanations

    say pl

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

    No Comments

    Negative Logits
    滚
    -20.75
     Schl
    -20.38
    .Att
    -18.25
     Att
    -18.00
    .progressBar
    -17.25
    懋
    -17.25
     impulse
    -17.00
    rolls
    -17.00
     Phelps
    -17.00
     Rolls
    -16.88
    POSITIVE LOGITS
    -pl
    19.63
     plat
    18.88
    Pl
    18.25
    	bl
    17.75
    ect
    17.63
    POSIT
    17.38
     Pl
    16.75
    oplast
    16.25
    /bl
    16.25
     Bl
    16.25
    Activations Density 1.269%

    No Known Activations