© 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. 2168
    Prev
    Next
    INDEX
    Explanations

    say "meth" words

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

    No Comments

    Negative Logits
     Territory
    -16.50
     Rotary
    -16.13
    aped
    -14.38
    .ev
    -13.31
    rowning
    -13.31
    示范区
    -13.25
    avery
    -13.13
    Έ
    -13.00
    豹
    -12.94
    rå
    -12.81
    POSITIVE LOGITS
    甲
    91.00
     meth
    87.50
     Meth
    82.50
    乙
    81.00
    meth
    78.50
    丙
    65.00
     methyl
    58.75
    eth
    56.75
     eth
    52.75
    戊
    52.50
    Activations Density 0.071%

    No Known Activations