© 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. 62955
    Prev
    Next
    INDEX
    Explanations

    pledge, principles, celebratory language

    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
    å½ĵåľ°äºº
    -0.08
     lol
    -0.07
     mostly
    -0.07
     plus
    -0.06
     Fou
    -0.06
    ç³
    -0.06
    yii
    -0.06
    èIJĮ
    -0.06
    Plus
    -0.06
     tricky
    -0.06
    POSITIVE LOGITS
     tonight
    0.09
     yesterday
    0.08
    ä»Ĭ次
    0.08
    egrity
    0.08
     Constitutional
    0.08
    æľ¬æ¬¡ä¼ļè®®
    0.08
     urgently
    0.08
     courageous
    0.08
    éľĢè¦ģæĪij们
    0.08
     unprecedented
    0.08
    Activations Density 0.623%

    No Known Activations