© 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. 11917
    Prev
    Next
    INDEX
    Explanations

    separate paper, opposite practice

    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
    ä½ıæĪ¿åĴĮ
    -0.08
    uks
    -0.07
     sär
    -0.07
    allocator
    -0.07
    uksi
    -0.07
     cả
    -0.07
    ελ
    -0.06
     обе
    -0.06
    aze
    -0.06
    unlink
    -0.06
    POSITIVE LOGITS
    ogos
    0.08
    vania
    0.07
    åį°ç¬¬
    0.07
    another
    0.07
    Another
    0.07
    Unnamed
    0.07
    è´µ
    0.07
    ä»Ĭ度ãģ¯
    0.07
    owo
    0.07
     another
    0.07
    Activations Density 0.356%

    No Known Activations