© 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. 14968
    Prev
    Next
    INDEX
    Explanations

    郭

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

    No Comments

    Negative Logits
    KV
    -19.88
    K
    -18.75
    _kv
    -18.50
    KS
    -18.38
     K
    -18.38
    estone
    -17.88
    _K
    -17.50
    禹
    -17.00
     Erick
    -17.00
    -K
    -16.88
    POSITIVE LOGITS
    alog
    17.38
    zos
    16.25
    geh
    15.88
    adle
    15.81
    ZH
    15.75
    阿拉伯
    15.75
    afs
    15.69
     Baghdad
    15.69
    ZR
    15.69
    lass
    15.50
    Activations Density 0.489%

    No Known Activations