© 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. 17880
    Prev
    Next
    INDEX
    Explanations

    metadata and semantic integration

    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
    Ỹ
    -0.08
    timing
    -0.08
    quine
    -0.08
    Timing
    -0.08
    ç»Ļæľĭåıĭ
    -0.08
    èĩ¨
    -0.07
    ewe
    -0.07
    ResponseType
    -0.07
     Shiv
    -0.07
     prestig
    -0.07
    POSITIVE LOGITS
     metadata
    0.14
     Metadata
    0.12
     semantic
    0.12
    semantic
    0.11
     hier
    0.10
    metadata
    0.10
     interoper
    0.10
    åħĥ
    0.10
    Metadata
    0.09
    (metadata
    0.09
    Activations Density 0.096%

    No Known Activations