© 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. 2723
    Prev
    Next
    INDEX
    Explanations

    say "sperm"

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

    No Comments

    Negative Logits
    霁
    -20.13
    network
    -17.00
     scarf
    -16.63
    烤
    -16.13
    琵
    -16.00
     networks
    -15.75
    DER
    -15.69
     Networks
    -15.63
    .snap
    -15.63
    .ribbon
    -15.44
    POSITIVE LOGITS
     sperm
    49.25
    精子
    44.75
     semen
    36.50
     ejac
    36.00
     sperma
    34.75
    生殖
    32.25
     ejaculation
    28.13
     sexually
    28.00
     sexual
    27.63
     Sexual
    27.50
    Activations Density 0.078%

    No Known Activations