© 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. 2445
    Prev
    Next
    INDEX
    Explanations

    Canadian, or company Inc

    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å¼Ģ
    -0.07
    رÙĬد
    -0.07
    ully
    -0.07
    满èħĶ
    -0.06
    ä¸Ģ空
    -0.06
    повÑĸда
    -0.06
    éĩijæ²Ļ
    -0.06
    enting
    -0.06
    å¼Ģæĭĵè¿Ľåıĸ
    -0.06
    ä¸įæĭĶ
    -0.06
    POSITIVE LOGITS
    bauer
    0.08
    ä¸Ĭå½ĵ
    0.08
    馴
    0.08
     symmetric
    0.08
    azón
    0.07
    对称
    0.07
    uble
    0.07
     Heard
    0.07
    Forms
    0.07
    incs
    0.07
    Activations Density 0.002%

    No Known Activations