© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2707
    Prev
    Next
    INDEX
    Explanations

    say "ed" words

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

    No Comments

    Negative Logits
    民
    -22.88
     eth
    -19.25
    记忆
    -17.00
    义
    -16.13
     pos
    -16.13
     memor
    -15.94
    极
    -15.38
    =pos
    -15.25
    val
    -14.94
    mem
    -14.94
    POSITIVE LOGITS
    Serialized
    22.13
    serialized
    21.25
     simulated
    20.63
     serialized
    20.50
     Serialized
    20.13
    Registered
    18.50
     mediated
    18.00
    registered
    17.75
     Registered
    17.63
    _RESERVED
    17.25
    Activations Density 0.213%

    No Known Activations