© 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. 1697
    Prev
    Next
    INDEX
    Explanations

    sexual

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

    No Comments

    Negative Logits
     sexual
    -30.13
     sexuality
    -27.63
     Sexual
    -26.25
     sexually
    -24.25
    axon
    -23.38
    SX
    -23.38
    Sex
    -22.13
     AX
    -21.75
     SX
    -21.50
     Sex
    -21.38
    POSITIVE LOGITS
    院长
    21.00
    副院长
    18.75
    CAL
    16.75
    院院长
    16.50
    -Cal
    16.38
    滇
    16.25
    charts
    15.56
    院
    15.50
    计算机
    15.13
     CALC
    15.00
    Activations Density 0.075%

    No Known Activations