© 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. 28936
    Prev
    Next
    INDEX
    Explanations

    cutting header of a harvesting machine

    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
    åľ¨å¿ĥä¸Ń
    -0.07
    èIJ½éŃĦ
    -0.07
    çģ«çĥ§
    -0.07
    微波çĤī
    -0.06
    åĪ°æľŁ
    -0.06
    åݨåį«
    -0.06
     prazo
    -0.06
    bound
    -0.06
    æķ²éŨ
    -0.06
    åľ¨ç½ij绾
    -0.06
    POSITIVE LOGITS
    æ¯ıåĪĨéĴŁ
    0.10
     conveyor
    0.09
    å·¥ä½į
    0.09
     rollers
    0.08
    å¸ĺ
    0.08
    é«ĺéĢŁ
    0.08
    åģľäºĨä¸ĭæĿ¥
    0.08
    åīįæĸ¹
    0.08
    çĶŁäº§çİĩ
    0.08
    æ¯ıçıŃ
    0.08
    Activations Density 0.432%

    No Known Activations