© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15467
    Prev
    Next
    INDEX
    Explanations

    say Qin

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

    No Comments

    Negative Logits
    党组织
    -19.25
    UDA
    -18.25
    保荐
    -15.06
     lod
    -15.00
    β
    -14.63
    入党
    -14.56
    批发市场
    -14.56
     salad
    -14.50
    LDAP
    -14.13
     lodging
    -14.06
    POSITIVE LOGITS
    秦
    31.63
    秦国
    23.63
    咸阳
    22.88
     Qin
    20.25
    嬴
    20.00
    秦皇
    18.50
    XS
    17.75
    XL
    17.50
     XL
    17.25
    秦皇岛
    17.00
    Activations Density 0.153%

    No Known Activations