© 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. 1100
    Prev
    Next
    INDEX
    Explanations

    say animal names

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

    No Comments

    Negative Logits
    Animal
    -24.13
    animal
    -24.13
     animal
    -23.88
     animals
    -23.00
    动物
    -22.38
     Animal
    -21.00
    urat
    -21.00
     wolf
    -21.00
    camel
    -20.75
     camel
    -20.38
    POSITIVE LOGITS
    Build
    16.75
     Build
    16.75
    建筑工程
    15.38
    工艺
    15.31
     math
    15.13
    瓶
    14.94
    Math
    14.75
     build
    14.44
    $menu
    14.25
    建筑
    14.19
    Activations Density 0.142%

    No Known Activations