© 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. 14420
    Prev
    Next
    INDEX
    Explanations

    say 8

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

    No Comments

    Negative Logits
    ieurs
    -15.06
    ide
    -14.88
    ��
    -14.75
    界
    -14.50
     comer
    -14.50
    舶
    -14.38
    竣
    -14.06
    urple
    -13.94
    reme
    -13.88
    阙
    -13.75
    POSITIVE LOGITS
    暹
    17.63
     SKF
    17.50
    nip
    16.13
     Camden
    15.69
    zego
    15.06
     EMC
    14.94
    senal
    14.69
    SError
    14.44
     Scot
    14.38
    CAP
    14.31
    Activations Density 0.008%

    No Known Activations