© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14696
    Prev
    Next
    INDEX
    Explanations

    say profanity

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

    No Comments

    Negative Logits
    樊
    -17.13
    发展模式
    -17.00
    坊
    -16.38
    getData
    -15.69
    滕
    -14.75
    chw
    -14.75
    公布了
    -14.56
    ousands
    -14.38
    .descriptor
    -14.25
    顾
    -14.25
    POSITIVE LOGITS
     fucking
    17.50
     Sexy
    17.13
     flavour
    15.56
     Fucking
    15.25
     poop
    15.06
     freaking
    14.88
     fucked
    14.25
     cena
    14.25
     sausage
    14.25
     boobs
    14.19
    Activations Density 0.257%

    No Known Activations