© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15640
    Prev
    Next
    INDEX
    Explanations

    say obscene

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

    No Comments

    Negative Logits
    �能
    -17.25
     strength
    -17.00
    控制系统
    -16.63
     weigh
    -16.50
    的力量
    -16.13
     strongest
    -15.94
    strength
    -15.94
    weigh
    -15.81
    绑定
    -15.75
    坚强
    -15.56
    POSITIVE LOGITS
    渎
    19.38
     pomp
    18.50
     saison
    18.25
    犊
    17.13
     seks
    16.88
     obscene
    16.38
     ejac
    16.38
     blasph
    16.00
     masturb
    15.75
     nostr
    15.69
    Activations Density 0.436%

    No Known Activations