© 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. 30128
    Prev
    Next
    INDEX
    Explanations

    twice

    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
    èĥ¤
    -0.07
    请填åĨĻ
    -0.06
    åĵī
    -0.06
    pty
    -0.06
    æħµ
    -0.06
    urai
    -0.06
    ç¿ħ
    -0.05
    ç¯ĩ
    -0.05
    ication
    -0.05
    åīįåĽŀ
    -0.05
    POSITIVE LOGITS
    çī¹çĤ¹æĺ¯
    0.08
    天ä¹ĭ
    0.08
    ä¾µçĬ¯äºĨæĤ¨çļĦ
    0.08
     Atlan
    0.08
    äºĭåĦ¿
    0.08
    éĺħè¯»æľ¬æĸĩ
    0.07
     Setia
    0.07
    代人
    0.07
    øv
    0.07
    åĮºãģ®
    0.07
    Activations Density 0.003%

    No Known Activations