© 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. 29805
    Prev
    Next
    INDEX
    Explanations

    Adler, Providence, Turkey, process

    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
    è¿ĺæľī个
    -0.08
    æŁIJç§įç¨ĭ度ä¸Ĭ
    -0.08
    Ø´Ùģ
    -0.08
    æ¯ĶæĪij们
    -0.07
    æľīçĤ¹åĥı
    -0.07
    çĶ¨åĪ°çļĦ
    -0.07
    ignano
    -0.07
    -leaning
    -0.07
    ForResource
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    POSITIVE LOGITS
    (*
    0.07
    çĢ
    0.06
    æ·»
    0.06
    NS
    0.06
    APT
    0.06
    浩çĦ¶
    0.06
    åºĶå½ĵä¾Ŀçħ§
    0.06
     гоÑģÑĥдаÑĢÑģÑĤвен
    0.06
    ErrorHandler
    0.06
     lawful
    0.06
    Activations Density 0.001%

    No Known Activations