© 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. 48206
    Prev
    Next
    INDEX
    Explanations

    diagrams and illustrations

    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
    èħĬ
    -0.08
    å§Ĩ
    -0.08
    以ä¸ĭåĩłçĤ¹
    -0.08
    ä¸ĭè¿°
    -0.07
    ems
    -0.07
    åºķä¸ĭ
    -0.07
    å¦Ĥä¸ĭ
    -0.07
    åºķä¸ĭçļĦ
    -0.07
    以ä¸ĭåĩł
    -0.07
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    -0.07
    POSITIVE LOGITS
    示æĦı
    0.10
    示æĦıåĽ¾
    0.09
     schematic
    0.09
    Typ
    0.08
    ç»ĵæŀĦ示æĦıåĽ¾
    0.08
    chematic
    0.08
    示ä¾ĭ
    0.08
     illustrating
    0.08
    åħ¸åŀĭçļĦ
    0.07
     proposed
    0.07
    Activations Density 0.040%

    No Known Activations