© 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. 1497
    Prev
    Next
    INDEX
    Explanations

    electrolyte

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

    No Comments

    Negative Logits
    电解
    -26.00
     electroly
    -26.00
     Electro
    -20.13
    Elect
    -17.00
    矩阵
    -16.50
    蓄电池
    -16.38
     electro
    -16.13
    mf
    -15.63
     batteries
    -15.31
     di
    -15.25
    POSITIVE LOGITS
     Food
    19.75
     food
    19.50
    食物
    19.38
     sound
    19.13
    Food
    18.75
    声音
    18.38
     voice
    17.25
     Sun
    17.25
    药
    17.25
    _food
    17.13
    Activations Density 0.130%

    No Known Activations