© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1443
    Prev
    Next
    INDEX
    Explanations

    dictionary

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

    No Comments

    Negative Logits
     dictionaries
    -35.25
     dictionary
    -34.00
    dictionary
    -32.25
     Dictionary
    -32.25
    .dictionary
    -30.75
    _dictionary
    -29.63
    Dictionary
    -28.50
    .Dictionary
    -28.00
    (dictionary
    -27.50
    字
    -27.38
    POSITIVE LOGITS
    Eng
    19.50
    -eng
    19.13
     engage
    18.63
     engaging
    18.63
     engagement
    18.50
    Earth
    18.38
     engaged
    18.25
     Eng
    18.13
    lights
    18.00
    earth
    18.00
    Activations Density 0.191%

    No Known Activations