© 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. 1268
    Prev
    Next
    INDEX
    Explanations

    [mountain] => [ous]

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

    No Comments

    Negative Logits
     mountain
    -55.00
     mountains
    -52.50
     Mountain
    -49.50
    山
    -49.00
    mount
    -48.25
    Mountain
    -47.75
     mount
    -46.00
     Mountains
    -45.25
    Mount
    -43.75
    山上
    -42.25
    POSITIVE LOGITS
     Bib
    16.25
    磷
    16.13
     epsilon
    15.75
    词
    15.56
    剧本
    15.19
    詞
    14.88
    пед
    14.56
     Ridley
    14.50
    剧
    14.25
     eps
    14.06
    Activations Density 0.111%

    No Known Activations