© 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. 1564
    Prev
    Next
    INDEX
    Explanations

    say clothing

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

    No Comments

    Negative Logits
    .console
    -18.00
    逻辑
    -18.00
    脑
    -17.88
     CBC
    -17.75
     cere
    -17.63
     CNS
    -17.38
     neurological
    -17.25
     logic
    -17.13
     Buenos
    -17.13
    神经系统
    -17.00
    POSITIVE LOGITS
    衣服
    17.38
    衣
    16.50
    Pi
    15.81
    服装
    15.31
    Berry
    15.19
     ethic
    15.13
    女装
    15.06
     Dial
    14.81
     paciente
    14.81
     Peach
    14.75
    Activations Density 0.076%

    No Known Activations