© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 708
    Prev
    Next
    INDEX
    Explanations

    say "hash"

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

    No Comments

    Negative Logits
    Luke
    -22.38
     Indiana
    -21.38
    Christopher
    -21.25
    詹姆
    -20.88
     Luke
    -20.88
     Wales
    -20.88
    约翰
    -20.63
    大卫
    -19.88
    威尔
    -19.50
    济宁
    -19.50
    POSITIVE LOGITS
    .tf
    25.75
     tf
    25.00
    (tf
    24.88
     HASH
    22.25
     Hash
    22.13
    _tf
    21.88
     TF
    21.25
    =tf
    20.50
     hash
    20.38
    (hash
    20.38
    Activations Density 0.246%

    No Known Activations