© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15350
    Prev
    Next
    INDEX
    Explanations

    say nomination

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

    No Comments

    Negative Logits
    MU
    -16.25
    瑛
    -16.00
    setParameter
    -15.81
    ميل
    -15.75
     Offset
    -15.75
     interfaces
    -15.63
    _lens
    -15.56
     Jihad
    -15.19
     offsets
    -15.13
     OFFSET
    -15.13
    POSITIVE LOGITS
     nominate
    16.63
    -runner
    16.38
     nomination
    16.13
     nominations
    15.56
     nominee
    14.88
    提名
    14.56
    Nom
    14.19
     Nom
    14.13
    パーティー
    13.94
    	run
    13.88
    Activations Density 0.082%

    No Known Activations