© 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. 49964
    Prev
    Next
    INDEX
    Explanations

    because or if

    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
    究竣æĺ¯
    -0.09
    ä¼¼ä¹İæĺ¯
    -0.09
    adero
    -0.08
    天éķ¿
    -0.08
    为ä»Ģä¹Īä¼ļ
    -0.08
    æĺ¯åIJ¦ä¼ļ
    -0.08
    åı¯èĥ½ä¼ļ被
    -0.08
    ä¼¼ä¹İä¹Ł
    -0.08
    究竣
    -0.07
    yll
    -0.07
    POSITIVE LOGITS
    atten
    0.07
    çŁ¥è¯ĨçļĦ
    0.07
    ãģĬãģĬ
    0.06
    æĻ°
    0.06
    à¼
    0.06
    ivel
    0.06
    çIJ¦
    0.06
    ContextHolder
    0.06
    对åħ¶
    0.06
    æ¸ī
    0.06
    Activations Density 0.005%

    No Known Activations