© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15401
    Prev
    Next
    INDEX
    Explanations

    say le

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

    No Comments

    Negative Logits
    琬
    -17.38
    洮
    -16.63
    珺
    -16.13
    GridColumn
    -16.00
    硕士
    -15.75
     Angie
    -15.50
    莊
    -15.31
     Riverside
    -15.19
     Kash
    -15.19
     REGISTER
    -15.06
    POSITIVE LOGITS
     le
    73.00
    (le
    70.50
    Le
    68.50
     Le
    67.00
    -le
    66.50
    le
    66.00
    .le
    64.50
    _le
    64.00
     LE
    63.00
    -Le
    60.25
    Activations Density 0.267%

    No Known Activations