© 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. 23671
    Prev
    Next
    INDEX
    Explanations

    functions, transformations, mapping

    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
     either
    -0.06
    [dir
    -0.06
    inah
    -0.06
    :
    -0.06
    áĥĶáĥijáĥĺ
    -0.06
    ijn
    -0.06
     cast
    -0.06
    _pending
    -0.06
     Evang
    -0.06
    æĮĩçĶ²
    -0.06
    POSITIVE LOGITS
    说åIJ§
    0.08
    äºĨä¹Ī
    0.08
    绣ä¸ĢåĪ°
    0.08
    å·¥ä½ľè¿Ľè¡ĮäºĨ
    0.08
    以ä¸ĭæĺ¯å°ıç¼ĸ
    0.08
    çĽ¸ä¼¼æĸĩçĮ®
    0.07
    มัà¹īย
    0.07
    AMES
    0.07
    ectos
    0.07
     Mapper
    0.07
    Activations Density 0.012%

    No Known Activations