© 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. 18178
    Prev
    Next
    INDEX
    Explanations

    number of episodes

    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
    太é«ĺ
    -0.08
    åѤ
    -0.08
     Singleton
    -0.08
    åģ¶å°Ķ
    -0.07
    åѤç«ĭ
    -0.07
     few
    -0.07
    èµı
    -0.07
    è¶ħéĩį
    -0.07
     isolated
    -0.07
     solitary
    -0.07
    POSITIVE LOGITS
    ç»Ĩå°ı
    0.12
     мелÑĮ
    0.11
    ç»Ĩå°ıçļĦ
    0.11
    è¿ĻäºĽå°ı
    0.11
    å¯Ĩå¯Ĩ麻麻
    0.11
    çIJIJç¢İ
    0.10
    ç´°ç·»
    0.10
    å¯ĨéĽĨ
    0.10
     мелкиÑħ
    0.10
    ç´°
    0.10
    Activations Density 0.071%

    No Known Activations