© 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. 16318
    Prev
    Next
    INDEX
    Explanations

    Transitional

    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
    æľīä¸Ģé»ŀ
    -0.06
    漫
    -0.06
    bito
    -0.06
    æ¦ľ
    -0.06
    ä¸ĢæŦ
    -0.06
    Ŀ
    -0.06
    éĻª
    -0.06
     vern
    -0.05
    æľīä¸ĢçĤ¹
    -0.05
    æĦģ
    -0.05
    POSITIVE LOGITS
    arrer
    0.11
    ä¸ĩåįĥ
    0.08
    Interop
    0.08
    ensee
    0.08
    åİŁä»¶åıĬ
    0.08
    erenc
    0.08
    endente
    0.08
    rtl
    0.07
    íĸīìĤ¬
    0.07
     Niest
    0.07
    Activations Density 0.004%

    No Known Activations