© 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. 30447
    Prev
    Next
    INDEX
    Explanations

    writing about software or projects

    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
     Cardoso
    -0.08
    åĽłåħ¬
    -0.07
    å±±ä¹ĭ
    -0.06
    å¼Ĭ
    -0.06
    çIJĨä¼ļ
    -0.06
    毫
    -0.06
    æĮĸæİĺåħ¬åı¸
    -0.06
    è¡į
    -0.06
    uisse
    -0.06
    elli
    -0.06
    POSITIVE LOGITS
    kent
    0.08
    azos
    0.08
    ptron
    0.08
    æĸ°æµªç½ij
    0.07
    arzy
    0.07
    rence
    0.07
    æł¡åºĨ
    0.07
    å¤įæŦ
    0.07
    Executor
    0.07
    allax
    0.07
    Activations Density 0.002%

    No Known Activations