© 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. 57118
    Prev
    Next
    INDEX
    Explanations

    things or equipment

    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
    /../
    -0.08
    åĴĮå·¥ä½ľ
    -0.08
    FunctionFlags
    -0.07
    ìłģìĿ´ê³ł
    -0.07
    ä¸ĥåħ«ç³Ł
    -0.07
    éĶ¦æłĩ
    -0.07
    å¤§ä½ľæĪĺ
    -0.07
    uvan
    -0.07
    å°ıåŃIJ
    -0.07
    çĤ¹å¤ļ
    -0.07
    POSITIVE LOGITS
    ç®Ģ称
    0.10
    以ä¸ĭç®Ģ称
    0.09
    åĬłæĭ¿å¤§
    0.08
    ä¿Ĺ称
    0.07
     Tbk
    0.07
     (
    0.06
    æĸ°åĬłåĿ¡
    0.06
    عة
    0.06
    簡稱
    0.06
    iasco
    0.06
    Activations Density 1.185%

    No Known Activations