© 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. 1825
    Prev
    Next
    INDEX
    Explanations

    say body parts

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

    No Comments

    Negative Logits
    姜
    -37.25
     sodium
    -36.50
    生姜
    -35.25
    钠
    -34.50
    	username
    -32.25
     Sodium
    -31.50
     Na
    -31.25
     shoulder
    -30.88
     username
    -30.88
    username
    -30.38
    POSITIVE LOGITS
    文本
    18.75
     nhạc
    18.63
     text
    18.13
     Telescope
    17.00
     newText
    16.63
     Token
    16.25
     instrumental
    16.00
    文字
    15.88
     Tokens
    15.75
    乐
    15.75
    Activations Density 0.114%

    No Known Activations