© 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. 14738
    Prev
    Next
    INDEX
    Explanations

    say 1

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

    No Comments

    Negative Logits
    妪
    -18.38
    ulia
    -18.38
    验
    -18.13
    Knight
    -18.00
    upt
    -18.00
    فس
    -17.88
    RK
    -17.75
    uest
    -17.75
    悫
    -17.63
     Mattis
    -17.50
    POSITIVE LOGITS
    (ev
    15.50
    (di
    14.06
     Ev
    13.13
    	ev
    12.56
     interfering
    12.25
    san
    12.19
    .ReadAll
    12.13
    阵
    12.13
    -di
    11.94
    _sid
    11.94
    Activations Density 0.040%

    No Known Activations