© 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. 28954
    Prev
    Next
    INDEX
    Explanations

    self, god, soul, consciousness

    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
    大æīĵ
    -0.09
    brig
    -0.08
    oup
    -0.08
    यà¥ĭà¤Ĺ
    -0.08
    æŃ£å¸¸çļĦ
    -0.07
    ryp
    -0.07
    é£ŁãģĦ
    -0.07
    æĬĬä¸Ģ个
    -0.07
    args
    -0.07
    ipy
    -0.07
    POSITIVE LOGITS
     abstract
    0.10
     inaccessible
    0.09
    èĻļæĹł
    0.09
    å®ŀä½ĵ
    0.09
     glimps
    0.08
     supreme
    0.08
    æľ¬ä½ĵ
    0.08
    涵åħ»
    0.08
     qualities
    0.08
     elusive
    0.08
    Activations Density 0.028%

    No Known Activations