© 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. 49227
    Prev
    Next
    INDEX
    Explanations

    German terms and specific concepts

    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
    urier
    -0.08
    ãĤĦãģ¤
    -0.07
    amba
    -0.07
    éĶŃ
    -0.07
    anden
    -0.06
    .inline
    -0.06
    å°ijèµ°
    -0.06
    åħĪè¡Į
    -0.06
    abouts
    -0.06
    olin
    -0.06
    POSITIVE LOGITS
    λÏĮ
    0.07
    bf
    0.06
    设计åĪ¶ä½ľ
    0.06
    å±±æĻ¯åĮº
    0.06
    æķĻèĤ²éĽĨåĽ¢
    0.06
    å·¥ä½ľæĢĿè·¯
    0.06
    ãĤŃãĥ£ãĥ³
    0.06
    ì¶Ķ
    0.06
    izan
    0.06
     francaise
    0.06
    Activations Density 0.033%

    No Known Activations