© 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. 1411
    Prev
    Next
    INDEX
    Explanations

    asking for help or clarification

    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
    âĢ¦
    -0.06
    è¦ģæ±Ĥåľ¨
    -0.06
    éĿŀ常çļĦ
    -0.06
    ç²īåĪ·
    -0.06
     cycles
    -0.06
    âĢ¦âĢ¦
    -0.06
    éĤ£ä¹ĪçļĦ
    -0.06
    æĢ¥
    -0.06
    (
    -0.06
    agen
    -0.06
    POSITIVE LOGITS
    çŃĶçĸij解æĥij
    0.08
    ä¸įå°ijç½ijåıĭ
    0.08
    å±ķå¼Ģåħ¨æĸĩ
    0.08
    ertext
    0.08
     spoilers
    0.07
    ussen
    0.07
    ãĤ¹ãĥĪãĥ¼
    0.07
    çİ®
    0.07
    {@
    0.07
    产åĵģæľįåĬ¡
    0.07
    Activations Density 0.011%

    No Known Activations