© 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. 3273
    Prev
    Next
    INDEX
    Explanations

    say friend

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     population
    -19.38
    阶段
    -18.88
    .population
    -18.88
    Population
    -18.25
     Population
    -18.13
    人口
    -17.25
    population
    -17.00
    元素
    -17.00
    _population
    -16.50
     populations
    -16.13
    POSITIVE LOGITS
     friend
    32.75
    friend
    31.75
    朋友
    31.63
     Friend
    28.63
    Friend
    28.38
    .friend
    28.25
    _friend
    26.38
     friendship
    25.25
     friends
    23.63
    	friend
    23.00
    Activations Density 0.057%

    No Known Activations