© 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. 20607
    Prev
    Next
    INDEX
    Explanations

    depths, position, indexPath

    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
    åı¯ä»¥å¤ļ
    -0.07
    æľ¬çīĪ
    -0.07
    çº¢ç´ł
    -0.06
     flat
    -0.06
    odin
    -0.06
    åĬŁåĪ©
    -0.06
    éŃ
    -0.06
    /cgi
    -0.06
    imo
    -0.06
    }s
    -0.06
    POSITIVE LOGITS
    æŀī
    0.09
    ä¸Ī
    0.08
    åĽ½åįİ
    0.08
    quires
    0.07
    æ¥ŀ
    0.07
    erschap
    0.07
    npos
    0.07
    ä½ķå¤Ħ
    0.07
    ×ķ×ijר
    0.07
    APPLE
    0.07
    Activations Density 0.006%

    No Known Activations