© 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. 29981
    Prev
    Next
    INDEX
    Explanations

    line breaks

    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
    天ä¸ĭ
    -0.07
     Sanc
    -0.07
    éĢļè¿ĩåĪĨæŀIJ
    -0.07
    lean
    -0.07
    anei
    -0.07
    inga
    -0.07
    ç»´
    -0.06
    _REMOVE
    -0.06
    ä¸Ģæĸ°
    -0.06
    æĹłä¸º
    -0.06
    POSITIVE LOGITS
    ç»Ń
    0.11
    æĭ¼æİ¥
    0.10
    çºĮ
    0.10
    æĭĨåĪĨ
    0.10
    _FRAGMENT
    0.09
    åĪĨæī¹
    0.09
    åĪĨ段
    0.09
    extension
    0.09
    PLIT
    0.08
     continu
    0.08
    Activations Density 0.233%

    No Known Activations