© 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. 11966
    Prev
    Next
    INDEX
    Explanations

    data serialization or encoding

    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
    ë¡Ŀ
    -0.07
    çĮ
    -0.07
    人头
    -0.07
    åħ´
    -0.07
    ç½®
    -0.07
    设å¤ĩå®īè£ħ
    -0.07
    pit
    -0.06
     Madr
    -0.06
    antro
    -0.06
    è¿ĺä¸į
    -0.06
    POSITIVE LOGITS
    serialized
    0.08
    äºijé¾Ļ
    0.08
     encoded
    0.08
    ASCII
    0.08
    Converted
    0.07
     invece
    0.07
    _encoded
    0.07
    Encoded
    0.07
    èģ·
    0.07
    èĥ³
    0.07
    Activations Density 0.004%

    No Known Activations