© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10082
    Prev
    Next
    INDEX
    Explanations

    article followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ones
    -0.07
    为ä»Ģä¹Īåij¢
    -0.07
    gend
    -0.07
    اش
    -0.07
    ÙħاÙĦ
    -0.06
    ecil
    -0.06
    arer
    -0.06
    emas
    -0.06
    rus
    -0.06
    ysts
    -0.06
    POSITIVE LOGITS
     particular
    0.12
     given
    0.09
    æĸĩ件æĪĸ
    0.08
     particulier
    0.08
     PARTICULAR
    0.08
    given
    0.08
    onese
    0.08
    æĬķèµĦæĪĸ
    0.07
     respective
    0.07
    ]'
    0.07
    Activations Density 0.314%

    No Known Activations