© 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. 56216
    Prev
    Next
    INDEX
    Explanations

    website or .com addresses

    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
    ãĥĦãĤ¤ãĥ¼ãĥĪ
    -0.08
    请ä¸İæĪij们èģĶç³»
    -0.08
    éĥ¨èIJ½å®¢
    -0.08
     Tweet
    -0.08
    åħ¶å®ĥåªĴä½ĵ
    -0.08
     Tweets
    -0.08
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    -0.07
    ç«ŀåĵģä¿¡æģ¯
    -0.07
    æĮĸæİĺåħ¬åı¸
    -0.07
    åħ³æ³¨åħ¬ä¼Ĺåı·
    -0.07
    POSITIVE LOGITS
     online
    0.13
    online
    0.11
     accessed
    0.11
     ìłijìĨį
    0.10
    ä¿¡æģ¯å¹³åı°
    0.10
     portal
    0.10
     website
    0.10
     Online
    0.09
    Online
    0.09
    -online
    0.09
    Activations Density 0.930%

    No Known Activations