© 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. 46736
    Prev
    Next
    INDEX
    Explanations

    provide or sell goods/services

    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
    æŀľæĸŃ
    -0.09
    zul
    -0.08
    hé
    -0.08
    æĶ¹éĿ©åıijå±ķ
    -0.07
    毫ä¸įçĬ¹è±«
    -0.07
    åıĪåĪ°äºĨ
    -0.07
    åŁºéĩijåħ¬åı¸
    -0.07
     dile
    -0.07
    akra
    -0.07
     famously
    -0.07
    POSITIVE LOGITS
    æĮĩå®ļ
    0.10
     expressly
    0.09
    约å®ļ
    0.09
    åıĮæĸ¹
    0.09
    åķĨå®ļ
    0.09
    约å®ļçļĦ
    0.09
    engu
    0.08
     specified
    0.08
    æĮĩå®ļåľ°çĤ¹
    0.08
    çijķçĸµ
    0.08
    Activations Density 0.062%

    No Known Activations