© 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. 20320
    Prev
    Next
    INDEX
    Explanations

    smaller, lesser, simpler

    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
     broaden
    -0.07
     broad
    -0.07
    绣çŃ¹
    -0.07
     broader
    -0.07
    å®ıè§Ĥ
    -0.06
    大æĺİ
    -0.06
     capitalized
    -0.06
    æĹłè¨Ģ
    -0.06
    亢
    -0.06
    .bold
    -0.06
    POSITIVE LOGITS
     smaller
    0.14
     lesser
    0.12
     lighter
    0.11
     softer
    0.11
     kleinere
    0.11
    è¾ĥå°ıçļĦ
    0.10
    ä½İèĩ³
    0.10
     simpler
    0.10
    ä¸Ńå°ıåŀĭ
    0.10
     Lesser
    0.10
    Activations Density 0.121%

    No Known Activations