© 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. 30440
    Prev
    Next
    INDEX
    Explanations

    chiral, approach, access

    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
     ess
    -0.08
    ļĮ
    -0.07
    æģ¤
    -0.07
    anan
    -0.07
    asc
    -0.07
    PJ
    -0.07
    ео
    -0.07
     asc
    -0.07
    orten
    -0.06
    åľ¨æľ¬ç«Ļ
    -0.06
    POSITIVE LOGITS
    ç«ĭä½ĵ
    0.08
    è¿ľç¦»
    0.08
     opposite
    0.08
    笳
    0.08
    å±ıèĶ½
    0.07
    åij¨åĽ´çݯå¢ĥ
    0.07
    lawanan
    0.07
    åıĹéĺ»
    0.07
    shield
    0.07
    è¿ĽæĿ¥çļĦ
    0.07
    Activations Density 0.005%

    No Known Activations