© 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. 15845
    Prev
    Next
    INDEX
    Explanations

    thought

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

    No Comments

    Negative Logits
    (signal
    -17.38
     Rahman
    -17.00
    签字
    -16.75
    /sign
    -16.00
    (rate
    -15.88
     signing
    -15.81
     sign
    -15.63
     signings
    -15.50
     rating
    -15.44
     signer
    -15.44
    POSITIVE LOGITS
    泳
    17.13
    unning
    15.44
     water
    15.38
    _WATER
    15.38
    processor
    15.19
    wald
    15.19
    用水
    15.00
    وان
    14.94
    agged
    14.94
    .currentThread
    14.81
    Activations Density 0.173%

    No Known Activations