© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 31730
    Prev
    Next
    INDEX
    Explanations

    horse based phrases

    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
    æĹłéĹ»
    -0.07
    ÙĴ
    -0.07
    олÑĮ
    -0.07
    aac
    -0.07
    oras
    -0.06
    anee
    -0.06
    iore
    -0.06
    汽水
    -0.06
    ifice
    -0.06
    èIJ¤çģ«
    -0.06
    POSITIVE LOGITS
    é©°éªĭ
    0.10
     лоÑĪа
    0.09
    horse
    0.09
     horses
    0.09
     horse
    0.09
     kuda
    0.09
    驹
    0.08
    åĿIJéªij
    0.08
     cavalry
    0.08
     Pferd
    0.08
    Activations Density 0.070%

    No Known Activations