© 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. 1524
    Prev
    Next
    INDEX
    Explanations

    heaven, hell, eternity

    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
     impun
    -0.09
    metro
    -0.08
    åĬ²
    -0.08
     impe
    -0.07
    itsu
    -0.07
    æĹĹé¼ĵ
    -0.07
    exas
    -0.07
    iya
    -0.07
    åħ¨æł¡
    -0.07
    åħ¨ç«Ļ
    -0.07
    POSITIVE LOGITS
     earthly
    0.09
    åįĩåħ¥
    0.09
     eternal
    0.09
    æŀģä¹IJ
    0.09
     everlasting
    0.09
     death
    0.08
     disemb
    0.08
     Death
    0.08
     awaiting
    0.08
    绵
    0.08
    Activations Density 0.046%

    No Known Activations