© 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. 2611
    Prev
    Next
    INDEX
    Explanations

    meta, metacognition, self-awareness

    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
    utherland
    -0.08
    夫æĸ¯åŁº
    -0.08
     jednos
    -0.08
    ÙģÙĪ
    -0.07
    ÅĽci
    -0.07
    ONSE
    -0.07
    讹
    -0.07
    aż
    -0.07
    èħĭ
    -0.07
     unjust
    -0.07
    POSITIVE LOGITS
     meta
    0.12
    /meta
    0.12
     Meta
    0.11
    meta
    0.11
    Meta
    0.11
    èĩªçľģ
    0.10
     reflexivity
    0.09
    .meta
    0.09
     awareness
    0.09
    _meta
    0.09
    Activations Density 0.028%

    No Known Activations