© 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. 2896
    Prev
    Next
    INDEX
    Explanations

    say mel

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

    No Comments

    Negative Logits
    ちは
    -14.81
    .pres
    -14.69
    =admin
    -14.63
     Gener
    -14.50
    -dat
    -14.31
    风雨
    -14.19
     digit
    -13.94
    regs
    -13.75
    ponent
    -13.75
    衮
    -13.69
    POSITIVE LOGITS
    Mel
    85.00
     Mel
    83.50
     mel
    81.50
    熔
    76.50
    mel
    75.50
     melting
    71.00
     melt
    70.50
     melts
    66.50
     melted
    62.25
     melan
    53.50
    Activations Density 0.217%

    No Known Activations