© 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. 20688
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
    åıĹ让
    -0.07
    .ak
    -0.07
    ummy
    -0.07
    enner
    -0.07
    .Syntax
    -0.07
     оÑĢганом
    -0.07
    áĥIJáĥĻ
    -0.07
    imir
    -0.07
    æĺ¯ä¸Ģ群
    -0.07
    ("").
    -0.07
    POSITIVE LOGITS
    ike
    0.07
    icken
    0.07
    inho
    0.07
    ä¾Ŀ
    0.07
    uden
    0.07
    kan
    0.06
    èĪŀæĽ²
    0.06
    ä¸Ģæ°Ķ
    0.06
    ital
    0.06
    ivel
    0.06
    Activations Density 0.133%

    No Known Activations