© 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. 56762
    Prev
    Next
    INDEX
    Explanations

    Penn State

    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
    еÑīа
    -0.09
    åħ·æľīå¾Ī强çļĦ
    -0.07
    æĪijå¿ĥ
    -0.06
    åħ·æľīè¾ĥ强çļĦ
    -0.06
    ornado
    -0.06
    æĪijçļĦç¥Ŀç¦ı
    -0.06
     ↵        ↵
    -0.06
     mend
    -0.06
    éĩĩçĶ¨çļĦæĺ¯
    -0.06
    åħ·æľīå¾Ī好çļĦ
    -0.06
    POSITIVE LOGITS
    æ¬
    0.08
    êng
    0.08
    plain
    0.08
    é¦ĸåħĪ
    0.08
     probably
    0.08
    tas
    0.08
    第ä¸Ģç¯ĩ
    0.08
    ks
    0.08
    Ãły
    0.07
    é¦ĸåħĪè¦ģ
    0.07
    Activations Density 0.001%

    No Known Activations