© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 49945
    Prev
    Next
    INDEX
    Explanations

    adverbial suffixes and conjunctive particles

    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
    åı¯èĥ½ä¼ļ导èĩ´
    -0.08
     possibly
    -0.08
     somehow
    -0.08
    åı¯èĥ½ä¼ļåĩºçݰ
    -0.07
    åı¯èĥ½å¯¼èĩ´
    -0.07
    ä½Ĩæĺ¯çͱäºİ
    -0.07
    æĪĸ许æĺ¯
    -0.07
    åı¯èĥ½ä¼ļ对
    -0.07
     subtly
    -0.07
     might
    -0.07
    POSITIVE LOGITS
    åĴĮæľĢ
    0.09
    认为
    0.08
    å±ĤéĿ¢ä¸Ĭ
    0.08
     tartal
    0.07
    etje
    0.07
    å°Ķé¡¿
    0.07
    otropic
    0.07
     ÑĢекомендÑĥем
    0.07
    åħ¬è®¤
    0.07
    åīįèĮħ
    0.07
    Activations Density 0.011%

    No Known Activations