© 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. 3720
    Prev
    Next
    INDEX
    Explanations

    colored complex formation

    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
    积æŀģæĢ§åĴĮ
    -0.07
    æĹ¥çĶ¨
    -0.07
    çIJ¢ç£¨
    -0.07
    æ±²
    -0.06
    åħĭåĬĽ
    -0.06
    å¿¿
    -0.06
    (reason
    -0.06
     Hammond
    -0.06
     bulk
    -0.06
    à§Ī
    -0.06
    POSITIVE LOGITS
     Detected
    0.08
    ibes
    0.08
    orii
    0.07
    olor
    0.07
    protocols
    0.07
    OLOR
    0.07
    å°Īæ¡Ī
    0.07
    æ£ĢæµĭåĪ°
    0.07
    åľ¨èIJ¥
    0.07
    å¼Ģåıijåĩº
    0.07
    Activations Density 0.006%

    No Known Activations