© 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. 14893
    Prev
    Next
    INDEX
    Explanations

    blood vessels

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

    No Comments

    Negative Logits
     QB
    -17.88
    pak
    -16.25
    _redirected
    -15.81
    vak
    -15.44
    PackageManager
    -15.25
    DirectoryName
    -15.19
     EQ
    -14.88
     BBB
    -14.81
    ndef
    -14.56
     PIN
    -14.38
    POSITIVE LOGITS
    与发展
    13.88
    .Input
    13.63
    inite
    13.38
    ))^
    13.13
    .Assembly
    13.06
     plage
    13.00
     arte
    12.75
    htag
    12.56
    contri
    12.56
    和发展
    12.44
    Activations Density 0.037%

    No Known Activations