© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1156
    Prev
    Next
    INDEX
    Explanations

    do not say dog

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

    No Comments

    Negative Logits
    狗
    -33.00
     dogs
    -31.75
     dog
    -31.50
    DOG
    -30.63
     Dog
    -30.50
     собак
    -29.25
    Dog
    -28.75
    狗狗
    -28.00
    犬
    -27.63
    dog
    -27.38
    POSITIVE LOGITS
    建筑材料
    16.88
    isman
    15.50
    ermen
    15.44
    icap
    14.31
    erman
    14.13
    装备制造
    13.63
    amination
    13.06
     media
    12.88
    影音
    12.75
     Calculator
    12.56
    Activations Density 0.097%

    No Known Activations