© 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. 21567
    Prev
    Next
    INDEX
    Explanations

    question about

    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
    çļĦåħ¶ä»ĸ
    -0.08
    çĥŃçĪ±ç¥ĸåĽ½
    -0.07
    ä»»ä½ķåħ¶ä»ĸ
    -0.07
    dje
    -0.07
    NSE
    -0.07
    lange
    -0.07
    æĺ¯æľ¬
    -0.07
    çī©ä»·å±Ģ
    -0.07
    åħ¶ä»ĸæĸ¹å¼ı
    -0.07
    æĺ¯æīĢæľī
    -0.07
    POSITIVE LOGITS
     ÑģкоÑĢее
    0.07
    zicht
    0.07
     apparently
    0.06
    _ranges
    0.06
     Trotz
    0.06
     supposedly
    0.06
    èģĮä¸ļåѦéĻ¢
    0.06
    çļĦä¸Ģ项éĩįè¦ģ
    0.06
    ä¸ŃçļĦä¸Ģç§į
    0.06
    éspedes
    0.06
    Activations Density 0.021%

    No Known Activations