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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15873
    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
     Evel
    -18.63
    TEL
    -17.38
    退市
    -17.25
    簟
    -17.13
    NFL
    -15.94
    RootElement
    -15.88
    看电视
    -15.75
    收费站
    -15.69
     subplot
    -15.56
    隽
    -15.56
    POSITIVE LOGITS
     hash
    48.50
    hash
    46.50
     hashes
    44.25
     HASH
    43.75
    Hash
    43.75
     Hash
    43.00
    _hash
    41.75
    -hash
    41.75
     hashing
    41.50
    哈
    41.50
    Activations Density 0.107%

    No Known Activations