© 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. 32943
    Prev
    Next
    INDEX
    Explanations

    integrated approaches and holistic strategy

    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
    两次
    -0.10
    两åĿĹ
    -0.08
    åħ©æ¬¡
    -0.08
    äºĮ人
    -0.08
    两çĤ¹
    -0.08
    éĢ¢
    -0.08
    oš
    -0.08
    opia
    -0.08
    两é¢Ĺ
    -0.08
    两类
    -0.07
    POSITIVE LOGITS
    综åIJĪ
    0.17
    çļĦ综åIJĪ
    0.17
    综åIJĪè¿IJçĶ¨
    0.16
    综åIJĪæĢ§
    0.16
    綾åIJĪ
    0.14
    综åIJĪèĢĥèĻij
    0.14
    综åIJĪæ²»çIJĨ
    0.14
    综åIJĪåĪĨæŀIJ
    0.14
    ç·ıåIJĪ
    0.13
    综åIJĪèĥ½åĬĽ
    0.13
    Activations Density 0.301%

    No Known Activations