© 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. 48262
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
    æĺ§
    -0.06
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.06
     Ferry
    -0.06
    ullets
    -0.06
     underneath
    -0.06
    æĪij们è¿ĺè¦ģ
    -0.06
    halt
    -0.06
    ä¸ĩæĪ·
    -0.06
    åįĥ家ä¸ĩæĪ·
    -0.06
    ë°±
    -0.05
    POSITIVE LOGITS
    åıĸåħ¶
    0.09
     ë°ĺë©´
    0.08
    ัà¸Ļà¸Ĺ
    0.08
     Sedangkan
    0.08
    abis
    0.08
    åı¦ä¸Ģæĸ¹éĿ¢
    0.07
    ÙĪاد
    0.07
    èĢĮæĺĵ
    0.07
    _particles
    0.07
    resp
    0.07
    Activations Density 0.138%

    No Known Activations