© 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. 15143
    Prev
    Next
    INDEX
    Explanations

    scientific writing

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

    No Comments

    Negative Logits
    浔
    -17.00
    黄埔
    -16.63
     TCL
    -16.63
     luaL
    -16.38
     NSK
    -15.69
    (rp
    -15.69
     bq
    -15.63
     Ubisoft
    -15.56
     Rowling
    -15.50
    桨
    -15.38
    POSITIVE LOGITS
    orig
    16.00
     followed
    15.69
     going
    15.50
     indeed
    15.44
     towards
    15.38
    ered
    15.38
     respectively
    15.19
    离开
    15.00
    c
    14.94
     otherwise
    14.94
    Activations Density 0.420%

    No Known Activations