© 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. 13342
    Prev
    Next
    INDEX
    Explanations

    average percentage annual

    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
    ãģ¾ãģ¤
    -0.08
    antie
    -0.08
    çļĦä¸Ģ对
    -0.08
    duk
    -0.08
    .nr
    -0.07
    utow
    -0.07
    é½IJåħ¨
    -0.07
     relaci
    -0.07
    ÑĬÑı
    -0.07
    áĥ¢áĥĺ
    -0.07
    POSITIVE LOGITS
    å¹³åĿĩ
    0.22
     average
    0.21
    çļĦå¹³åĿĩ
    0.21
     averaged
    0.20
     averages
    0.19
    average
    0.19
     avg
    0.19
    å¹³åĿĩåĢ¼
    0.18
     averaging
    0.18
    å¹³åĿĩæ°´å¹³
    0.18
    Activations Density 0.144%

    No Known Activations