© 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. 17182
    Prev
    Next
    INDEX
    Explanations

    discovery or discovered

    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
    æĿ¥éĢīæĭ©
    -0.07
    çĶŁåľ¨
    -0.06
     applied
    -0.06
    é¾Ł
    -0.06
    çĿĢ
    -0.06
    éĢīçĶ¨
    -0.06
    çĿĢæĪij
    -0.06
    çĿĢä¸Ģ
    -0.06
    vestment
    -0.06
    çĤ³
    -0.06
    POSITIVE LOGITS
     discovery
    0.15
    åıijçİ°
    0.15
    åıijçİ°äºĨ
    0.14
    åıijçİ°çļĦ
    0.14
    çĻ¼çı¾
    0.14
     discoveries
    0.14
     اÙĥتشاÙģ
    0.13
     ë°ľê²¬
    0.13
    çļĦåıijçİ°
    0.13
     Discovery
    0.13
    Activations Density 0.419%

    No Known Activations