© 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. 17067
    Prev
    Next
    INDEX
    Explanations

    text and string manipulation

    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
    -equipped
    -0.07
    گاÙĩ
    -0.07
     Bagi
    -0.07
     equip
    -0.07
    èķĬ
    -0.07
    eges
    -0.07
    åĽ¾ç½ij
    -0.07
    æĪIJ群
    -0.06
    ç®Ĺ
    -0.06
    ersh
    -0.06
    POSITIVE LOGITS
     text
    0.10
     prose
    0.09
    ä¸Ńèĭ±æĸĩ
    0.09
    ä¸ŃæıIJåıĸ
    0.09
     extract
    0.08
     excerpt
    0.08
    ä¸ŃåĮħåIJ«
    0.08
    ä¸ŃåIJ«
    0.08
    è¿Ļ段
    0.08
     corpus
    0.08
    Activations Density 0.050%

    No Known Activations