© 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. 15837
    Prev
    Next
    INDEX
    Explanations

    say "in" words

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

    No Comments

    Negative Logits
     rời
    -17.13
    辘
    -17.00
     tid
    -16.75
    炬
    -16.25
    辫
    -16.00
     Ellis
    -15.88
     Bridge
    -15.56
    墀
    -15.50
    tere
    -15.38
     Wick
    -15.19
    POSITIVE LOGITS
    inf
    44.75
    イン
    42.50
    Inf
    42.25
     INF
    41.25
    _inf
    40.50
     Inf
    40.50
    INF
    40.50
     inf
    38.25
    _INF
    37.50
    /in
    37.00
    Activations Density 0.368%

    No Known Activations