© 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. 62793
    Prev
    Next
    INDEX
    Explanations

    mathematical indices like n and k

    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
     Burns
    -0.07
    ief
    -0.06
    äºĴ
    -0.06
    å°ļ书
    -0.06
    è°
    -0.06
    itech
    -0.06
    æĭĴ
    -0.06
    çģ¼
    -0.06
    رائ
    -0.06
     Cory
    -0.06
    POSITIVE LOGITS
    abad
    0.08
    irme
    0.08
    åľŁçŁ³
    0.08
    ICLE
    0.08
    áĢĦáĢºáĢ¸
    0.08
    chetto
    0.07
    каÑĥ
    0.07
    wiek
    0.07
    :date
    0.07
    åIJijãģį
    0.07
    Activations Density 0.004%

    No Known Activations