© 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. 1716
    Prev
    Next
    INDEX
    Explanations

    equator

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

    No Comments

    Negative Logits
     sound
    -18.38
    ATO
    -17.88
    唾
    -16.88
    SEN
    -16.13
    sound
    -16.00
    喉咙
    -15.69
    声音
    -15.56
     Sound
    -15.56
    声道
    -15.56
    聋
    -15.44
    POSITIVE LOGITS
    ableObject
    14.69
    不负
    14.19
    ownload
    14.13
    游戏
    13.81
    禋
    13.75
    作物
    13.63
     télécharg
    13.56
    游戏中
    13.50
    omer
    13.31
    植物
    13.19
    Activations Density 0.068%

    No Known Activations