© 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. 48408
    Prev
    Next
    INDEX
    Explanations

    elements and materials

    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
    bund
    -0.07
     dere
    -0.07
    çĬ¶
    -0.07
    à¹Īà¸ĩ
    -0.06
     Gardens
    -0.06
    éĴ
    -0.06
     Jardin
    -0.06
     Lime
    -0.06
    ä»Ķ
    -0.06
    çĭĢ
    -0.06
    POSITIVE LOGITS
    ikli
    0.10
    ://{
    0.09
    licity
    0.08
    rian
    0.08
    vim
    0.07
    -lined
    0.07
    åĪ¶æĪIJçļĦ
    0.07
    mtree
    0.07
    åģļæĪIJçļĦ
    0.07
    éĩĮæĺĤ
    0.07
    Activations Density 0.511%

    No Known Activations