© 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. 62954
    Prev
    Next
    INDEX
    Explanations

    ownership or control structure

    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
    æ´»åľ¨
    -0.07
    åĽĽåij¨
    -0.07
     ÑģпÑĢав
    -0.06
    d
    -0.06
    å¤ļçĶ¨
    -0.06
     fejl
    -0.06
    亲çĪ±çļĦ
    -0.06
     thr
    -0.06
    åħī顾
    -0.06
    jala
    -0.06
    POSITIVE LOGITS
    æĮģèĤ¡æ¯Ķä¾ĭ
    0.11
    æĮģæľīçļĦ
    0.11
    æĮģèĤ¡
    0.10
    æīĢæĮģ
    0.10
     holdings
    0.10
    åĩºèµĦé¢Ŀ
    0.09
     Ownership
    0.09
     ownership
    0.09
    èĤ¡æĿĥ
    0.09
    èĩªçĦ¶äºº
    0.09
    Activations Density 0.093%

    No Known Activations