© 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. 16212
    Prev
    Next
    INDEX
    Explanations

    say "am"

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

    No Comments

    Negative Logits
    inge
    -18.50
    kc
    -17.38
     sting
    -17.25
    las
    -17.13
    zed
    -17.13
     Lis
    -17.00
     kc
    -16.75
    kas
    -16.13
    vez
    -16.13
    <w
    -16.13
    POSITIVE LOGITS
    ANNOT
    18.38
    imity
    17.50
    同业
    17.38
    amar
    16.38
    牦
    16.13
    annot
    16.13
    天花
    15.88
    弇
    15.81
    ató
    15.69
    ampus
    15.63
    Activations Density 0.002%

    No Known Activations