© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15718
    Prev
    Next
    INDEX
    Explanations

    say blood

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

    No Comments

    Negative Logits
    黍
    -18.25
     Kurd
    -17.00
    cookie
    -16.13
    comfort
    -15.88
    _cookies
    -15.75
    ghi
    -15.69
    原子
    -15.63
    coeff
    -15.63
    Krist
    -15.00
     coal
    -14.81
    POSITIVE LOGITS
     blood
    32.00
    血
    31.00
    blood
    31.00
     Blood
    29.88
     flow
    29.88
    Blood
    28.75
    血液
    27.75
    flow
    27.13
     flows
    26.63
     bloodstream
    26.63
    Activations Density 0.251%

    No Known Activations