© 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. 2107
    Prev
    Next
    INDEX
    Explanations

    say "mel" words

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

    No Comments

    Negative Logits
     pos
    -15.31
    绳
    -15.19
    scratch
    -14.75
    osphere
    -14.56
    digit
    -14.50
     Ferd
    -14.50
    琮
    -14.38
    Ğ
    -14.38
    苕
    -14.38
     cert
    -14.31
    POSITIVE LOGITS
     Mel
    66.50
    Mel
    65.00
     melan
    64.50
     mel
    59.00
    mel
    58.75
    熔
    36.50
     Melanie
    35.00
     melting
    34.50
     melt
    31.88
     melts
    30.25
    Activations Density 0.037%

    No Known Activations