© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3052
    Prev
    Next
    INDEX
    Explanations

    say "mineral"

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

    No Comments

    Negative Logits
    乙方
    -20.88
    [obj
    -16.50
     ret
    -16.00
     obj
    -15.44
    =obj
    -15.31
    evin
    -15.25
     Pil
    -15.00
     param
    -14.94
    (obj
    -14.88
     Capt
    -14.81
    POSITIVE LOGITS
     mineral
    55.00
    矿
    50.75
     Mineral
    49.75
     minerals
    45.25
    矿物质
    43.00
    Min
    41.00
    min
    37.25
     Minerals
    37.00
     Miner
    36.50
     Min
    36.25
    Activations Density 0.111%

    No Known Activations