© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17119
    Prev
    Next
    INDEX
    Explanations

    pass citizenship, eligibility, upgrade

    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
    avers
    -0.09
    è¾±
    -0.07
    enis
    -0.07
    entine
    -0.07
    azos
    -0.07
    .pad
    -0.07
    igon
    -0.06
    eus
    -0.06
     chÃŃ
    -0.06
    å°ģ
    -0.06
    POSITIVE LOGITS
     according
    0.09
    æł¹æį®åħ¶
    0.09
    æĮīçħ§
    0.08
    æł¹æį®
    0.08
    according
    0.08
     ÑģоглаÑģно
    0.08
     gemÃ¤ÃŁ
    0.08
     pagal
    0.08
    According
    0.07
    ccording
    0.07
    Activations Density 0.029%

    No Known Activations