© 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. 32899
    Prev
    Next
    INDEX
    Explanations

    code and structure

    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
    alist
    -0.08
    çĸ¡
    -0.08
    ieras
    -0.08
    å°ĶèĴĻ
    -0.08
    PerPixel
    -0.08
    émat
    -0.08
    venÃŃ
    -0.08
     DeepCopy
    -0.08
    ÙħÙĪÙĦ
    -0.08
    rell
    -0.08
    POSITIVE LOGITS
    ä¸ĭå±±
    0.07
    è¾Ĺ转
    0.07
    hausen
    0.06
     Dixon
    0.06
    osz
    0.06
     gcd
    0.06
    交æį¢
    0.06
    anas
    0.06
    第ä¸Ģè½®
    0.06
    ä»Ĭ天æĪij们
    0.06
    Activations Density 0.001%

    No Known Activations