© 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. 14037
    Prev
    Next
    INDEX
    Explanations

    increasing or decreasing values

    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
    urent
    -0.09
    inte
    -0.08
    æŃ£å¼ıçļĦ
    -0.08
    à¹Īà¸Ńà¸Ļ
    -0.08
    teni
    -0.08
    åī¯æĢ»
    -0.08
    wski
    -0.08
    å·¥ä½ľæĬ¥åijĬ
    -0.08
    ustin
    -0.07
    æĸ¹å¼ı为
    -0.07
    POSITIVE LOGITS
    éļıé£İ
    0.06
    ä¹Łéļıä¹ĭ
    0.06
    éļıçĿĢ
    0.06
    æķ°åĢ¼
    0.06
    —and
    0.06
    lug
    0.06
    а
    0.06
    æĺ¾èijĹ
    0.06
    é¾Ħ
    0.06
    ائر
    0.06
    Activations Density 0.004%

    No Known Activations