© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14863
    Prev
    Next
    INDEX
    Explanations

    say non-Latin

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

    No Comments

    Negative Logits
    aper
    -18.75
     Connor
    -18.13
    akin
    -17.63
    泉
    -17.63
    APH
    -17.50
    uf
    -17.25
     Erin
    -16.75
    aph
    -16.63
     derp
    -16.63
    吠
    -16.38
    POSITIVE LOGITS
    屏障
    18.75
    estre
    17.13
    奥斯卡
    16.63
     joystick
    15.94
    悬挂
    15.81
    梧
    15.75
    桓
    15.38
    天花板
    15.31
    illos
    15.19
    сос
    15.00
    Activations Density 0.926%

    No Known Activations