© 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. 2574
    Prev
    Next
    INDEX
    Explanations

    possessive nouns or plural forms

    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
    ÅĦczy
    -0.08
    人æĸĩ
    -0.07
    atz
    -0.07
    è¶ĭåĬ¿
    -0.07
    -ish
    -0.07
    ieux
    -0.06
    onium
    -0.06
    äºĮ度
    -0.06
    ajos
    -0.06
    ä¸Ģæŀļ
    -0.06
    POSITIVE LOGITS
    ãģ¿ãģ®
    0.09
    ãģķãĤī
    0.09
    âĤ¬âĦ¢
    0.08
    代ãĤıãĤĬãģ«
    0.08
    许å¤ļ
    0.08
    íļĮìĿĺ
    0.08
    å¤į
    0.08
     fortunes
    0.08
    åĪ°ä¾Ĩ
    0.07
     kanssa
    0.07
    Activations Density 0.317%

    No Known Activations