© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14567
    Prev
    Next
    INDEX
    Explanations

    villages

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

    No Comments

    Negative Logits
    规范
    -17.00
    school
    -16.38
    _GPU
    -15.94
    呐
    -15.69
    arend
    -15.63
    .Signal
    -15.44
    对话
    -14.69
    说话
    -14.63
    .prom
    -14.44
    groupBox
    -14.31
    POSITIVE LOGITS
    ophil
    13.81
    ophile
    13.69
    该县
    13.63
    逦
    13.50
    村子
    13.06
    风吹
    12.94
    该村
    12.94
    сон
    12.88
    -assets
    12.88
    orem
    12.81
    Activations Density 0.139%

    No Known Activations