© 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. 62579
    Prev
    Next
    INDEX
    Explanations

    patent claims processing

    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
    ArrayOf
    -0.07
    ±
    -0.07
    çľ¼äºĨ
    -0.06
    $$$
    -0.06
    è¿ĩåİ»
    -0.06
    .ly
    -0.06
    .apps
    -0.06
    I
    -0.06
     something
    -0.06
    .Valid
    -0.06
    POSITIVE LOGITS
    naval
    0.08
    ROID
    0.08
    αιο
    0.07
    à¹Ģà¸ĸ
    0.07
    ename
    0.07
     kritis
    0.07
    RTL
    0.07
    èļĮ
    0.07
    ела
    0.07
    ä»»ä½ķçļĦ
    0.07
    Activations Density 0.001%

    No Known Activations