© 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. 15291
    Prev
    Next
    INDEX
    Explanations

    say "9"

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

    No Comments

    Negative Logits
    十二
    -15.44
     Collins
    -14.94
     rub
    -14.69
     sty
    -14.50
    十六
    -14.44
     sixteen
    -14.06
    COL
    -14.00
    mars
    -14.00
    大理石
    -13.88
    卷
    -13.81
    POSITIVE LOGITS
    erno
    18.00
    ãn
    17.63
    umno
    17.13
    anter
    16.13
    enary
    15.94
    umn
    15.69
     ch
    15.44
    (ch
    15.38
     Chan
    15.31
    *sp
    15.13
    Activations Density 0.012%

    No Known Activations