© 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. 15024
    Prev
    Next
    INDEX
    Explanations

    1066

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

    No Comments

    Negative Logits
    STANCE
    -15.94
    elper
    -15.81
    ocache
    -15.25
    .rmi
    -15.13
    andler
    -14.44
     enclosed
    -14.44
     RouteServiceProvider
    -14.38
    cel
    -14.19
    PLIED
    -14.06
    .Rad
    -14.00
    POSITIVE LOGITS
    bz
    14.44
    жить
    14.06
    kad
    13.81
     spun
    13.63
     photographic
    13.56
    omb
    13.50
    OMB
    13.44
    бав
    13.31
    Advertisements
    13.00
    OVER
    12.50
    Activations Density 0.024%

    No Known Activations