© 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. 2166
    Prev
    Next
    INDEX
    Explanations

    say init

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

    No Comments

    Negative Logits
    erval
    -22.00
     relation
    -17.75
    .eth
    -17.13
    relation
    -16.75
     verify
    -16.50
    (protocol
    -16.38
    丁
    -16.25
    (annotation
    -16.00
     relations
    -15.94
     Relation
    -15.88
    POSITIVE LOGITS
    始
    31.38
    Ter
    29.63
     Ter
    26.25
     Init
    24.75
     ter
    23.88
    TER
    23.00
    Init
    22.63
    init
    21.75
    termin
    21.00
     initiation
    20.88
    Activations Density 0.087%

    No Known Activations