© 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. 58470
    Prev
    Next
    INDEX
    Explanations

    species density and diversity

    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
    å½ĵåľ°çļĦ
    -0.08
    å½ĵåľ°æĶ¿åºľ
    -0.07
    ظ
    -0.07
    äºĽè®¸
    -0.07
    éĴĪ对æĢ§çļĦ
    -0.07
    éĻIJæŶ
    -0.07
    å½ĵåľ°
    -0.07
    éĴĪ对
    -0.07
    ucker
    -0.07
    éĴĪ对æĢ§
    -0.07
    POSITIVE LOGITS
    åįłåħ¨åĽ½
    0.09
    æĺ¯åħ¨åĽ½
    0.08
    æĺ¯ä¸ĸçķĮä¸Ĭ
    0.08
    éŨ类
    0.08
    edException
    0.08
    æĺ¯ä¸Ńåįİæ°ijæĹı
    0.08
    é«ĺçŃīéĻ¢æł¡
    0.07
    éĿ¢ä¸´çĿĢ
    0.07
    Registrar
    0.07
    ä¸ī大
    0.07
    Activations Density 0.026%

    No Known Activations