© 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. 2063
    Prev
    Next
    INDEX
    Explanations

    say "dict"

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

    No Comments

    Negative Logits
     reserve
    -22.38
    reserve
    -20.75
     Reserve
    -20.75
    reserved
    -20.25
    Res
    -19.75
    [res
    -19.63
     Res
    -19.63
    余
    -19.13
    =res
    -19.13
     reserved
    -19.00
    POSITIVE LOGITS
     dict
    47.75
    dict
    45.00
     dicts
    41.25
     Dict
    41.25
    Dict
    41.00
    (dict
    39.25
    .dict
    37.75
    _dict
    32.00
     dictate
    31.50
    典
    31.50
    Activations Density 0.095%

    No Known Activations