© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 28303
    Prev
    Next
    INDEX
    Explanations

    situations needing resolution or action

    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
    æĸ°æĹ¶ä»£çļĦ
    -0.07
    ItemType
    -0.06
    unyi
    -0.06
    ä¸ĬçŃī
    -0.06
     dout
    -0.06
    å¸ĮæľĽåĴĮ
    -0.06
    chien
    -0.06
    ×Ļש
    -0.06
    éĤ¦
    -0.06
    วม
    -0.06
    POSITIVE LOGITS
    åĢĴéĢ¼
    0.09
     поÑĤÑĢебо
    0.09
    åľ¨è¿Ļ个è¿ĩç¨ĭä¸Ń
    0.09
    éĶ»çĤ¼äºĨ
    0.08
     تتطÙĦب
    0.08
    å¿ħçĦ¶
    0.08
     ê³¼ìłķìĹIJìĦľ
    0.08
    çļĦè¿ĩç¨ĭä¸Ń
    0.08
    requ
    0.08
     erfordert
    0.08
    Activations Density 0.148%

    No Known Activations