© 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. 50964
    Prev
    Next
    INDEX
    Explanations

    dust particles and accumulation

    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
    活水
    -0.09
    istically
    -0.07
    ALLY
    -0.07
    istik
    -0.07
     Cristina
    -0.06
     darurat
    -0.06
    .fromCharCode
    -0.06
    retty
    -0.06
    emann
    -0.06
    istische
    -0.06
    POSITIVE LOGITS
     dust
    0.10
     Dust
    0.10
    塵
    0.10
    å°ĺåľŁ
    0.09
    çģ°å°ĺ
    0.09
    à¸Ŀุà¹Īà¸Ļ
    0.09
    å°ĺåŁĥ
    0.09
     пÑĭли
    0.09
     má»ĭn
    0.09
    IJ
    0.08
    Activations Density 0.017%

    No Known Activations