© 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. 48746
    Prev
    Next
    INDEX
    Explanations

    desire to achieve

    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
    åıĹçĽĬåĮªæµħ
    -0.06
    iasm
    -0.06
    æĩĴå¾Ĺ
    -0.06
    éľĢ注æĦı
    -0.06
    laus
    -0.06
    èĩªåĺ²
    -0.06
    ä¸¥æł¼è¦ģæ±Ĥ
    -0.06
    avery
    -0.06
    éĿ¢åIJijåħ¨åĽ½
    -0.06
    Susp
    -0.06
    POSITIVE LOGITS
    å¿«çĤ¹
    0.12
     möglichst
    0.11
    尽快
    0.10
    赶快
    0.10
    æĹ©æĹ¥
    0.09
    å°ijãģĹãģ§ãĤĤ
    0.09
    çļĦä¸įæĺ¯
    0.09
    çļĦå°±æĺ¯
    0.09
    ä½ķãģ¨ãģĭ
    0.09
    ä¸įæĥľ
    0.08
    Activations Density 0.329%

    No Known Activations