© 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. 27059
    Prev
    Next
    INDEX
    Explanations

    ahead of schedule

    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
     Worse
    -0.09
     worse
    -0.08
     :(
    -0.08
    åħ¼å®¹æĢ§
    -0.08
    åĬłéĩį
    -0.07
    compat
    -0.07
    rob
    -0.07
    egu
    -0.07
    ç³Ł
    -0.07
    ä¸įå¦ĤæĦı
    -0.07
    POSITIVE LOGITS
     mát
    0.10
    å¾ĹçĽĬäºİ
    0.09
     clean
    0.08
    å½ĴåĬŁäºİ
    0.08
    åĩıè´Ł
    0.08
    .Async
    0.08
     bersih
    0.08
    æ¸ħçĪ½
    0.08
    æ¸ħåĩī
    0.08
     nhá»Ŀ
    0.08
    Activations Density 0.226%

    No Known Activations