© 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. 14417
    Prev
    Next
    INDEX
    Explanations

    say names

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

    No Comments

    Negative Logits
    iad
    -15.69
    侨
    -15.56
    adow
    -15.44
    翎
    -15.31
    cia
    -15.31
    alia
    -15.19
    _AG
    -15.06
    vis
    -14.88
    ↔
    -14.56
    aned
    -14.44
    POSITIVE LOGITS
    raj
    16.63
     HOLDER
    16.63
    𝑗
    16.50
    jer
    16.25
    Jones
    16.13
    煅
    15.94
     joe
    15.19
    :j
    15.06
    licenses
    15.00
     Kaiser
    14.94
    Activations Density 0.549%

    No Known Activations