© 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. 60519
    Prev
    Next
    INDEX
    Explanations

    data streams and key/value pairs

    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
    oses
    -0.07
    æĤ¼
    -0.07
    bard
    -0.07
    亿港åħĥ
    -0.07
     Â
    -0.06
     contado
    -0.06
    MBER
    -0.06
    åIJĪåĶ±
    -0.06
    íĹ
    -0.06
    γÏģα
    -0.06
    POSITIVE LOGITS
    éľĨ
    0.08
    _generated
    0.07
    Ñĥма
    0.07
    åĩºäºº
    0.07
     Expires
    0.07
    å¨ľ
    0.07
    西æŀĹ
    0.07
    Injected
    0.07
    DataStream
    0.06
    ãģĦãĤį
    0.06
    Activations Density 0.074%

    No Known Activations