© 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. 15020
    Prev
    Next
    INDEX
    Explanations

    [the] => [the]

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

    No Comments

    Negative Logits
    lycer
    -18.50
    ⽯
    -17.63
     wolf
    -16.75
    .ly
    -16.13
    _java
    -16.13
    jal
    -16.00
    俄
    -15.94
    �
    -15.81
    cribes
    -15.31
    inue
    -15.25
    POSITIVE LOGITS
     shortened
    14.38
    腥
    13.38
    Indexed
    13.31
    缩短
    13.25
    izzle
    13.00
    flare
    12.69
    ,nil
    12.56
     xứ
    12.56
    桀
    12.56
    乡土
    12.44
    Activations Density 0.061%

    No Known Activations