© 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. 20826
    Prev
    Next
    INDEX
    Explanations

    if used to introduce situations

    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
    åıĪéģĵ
    -0.07
    åij½è¿IJçļĦ
    -0.07
    ç½®ä¹ĭ
    -0.07
    æĸ°éĹ»å®¢æĪ·ç«¯
    -0.07
    Unsafe
    -0.07
    unsafe
    -0.06
    è§ģ她
    -0.06
     Coleman
    -0.06
    ä¸į容
    -0.06
    ampf
    -0.06
    POSITIVE LOGITS
    æł¹æľ¬æ²¡æľī
    0.12
    ä¸įåŃĺåľ¨
    0.10
    æł¹æľ¬å°±æ²¡æľī
    0.10
    æĹłåīį
    0.09
    æł¹æľ¬å°±
    0.09
    æļĤæĹ¶æ²¡æľī
    0.09
    æĹłä»İ
    0.09
    æĢİä¹Īå¤ĦçIJĨ
    0.09
    æĢİä¹ĪåĬŀ
    0.08
    æī¾ä¸įåĪ°
    0.08
    Activations Density 0.138%

    No Known Activations