© 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. 15960
    Prev
    Next
    INDEX
    Explanations

    say jump

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

    No Comments

    Negative Logits
    修
    -19.00
     Oslo
    -18.88
    ensor
    -18.00
     Café
    -17.00
    wald
    -16.50
    饰品
    -16.13
     bestellen
    -15.94
     Cafe
    -15.63
    療
    -15.56
     Odin
    -15.38
    POSITIVE LOGITS
     jump
    20.25
    爆发
    19.88
     jumping
    19.63
    jump
    19.50
    跳
    18.63
     Jump
    18.50
     explos
    18.50
     jumps
    18.25
    _JUMP
    17.75
    Jump
    17.63
    Activations Density 0.096%

    No Known Activations