© 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. 38004
    Prev
    Next
    INDEX
    Explanations

    present invention

    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
    hausen
    -0.08
     cykl
    -0.08
    unya
    -0.08
    egger
    -0.08
    æĦĪæ¼ĶæĦĪ
    -0.08
    à¸Ĺั
    -0.08
    hofer
    -0.08
    hme
    -0.08
    еÑģе
    -0.08
    esco
    -0.08
    POSITIVE LOGITS
    èİ·èµŀ
    0.07
    积累äºĨ
    0.07
    puis
    0.07
    å¤Ħ女座
    0.06
    accum
    0.06
    Posts
    0.06
    SetUp
    0.06
    ç©į
    0.06
     verified
    0.06
    igel
    0.06
    Activations Density 0.021%

    No Known Activations