© 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. 60311
    Prev
    Next
    INDEX
    Explanations

    passive and ive endings

    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
    anity
    -0.09
    egar
    -0.08
    ÑĦÑĤ
    -0.07
    edo
    -0.07
    ekom
    -0.07
    æĦıæ°Ķ
    -0.07
    hov
    -0.07
    eko
    -0.07
    ÙĤدر
    -0.07
    meal
    -0.07
    POSITIVE LOGITS
    æĹłä¸º
    0.09
    ãģªãģĮãĤī
    0.09
    ÙĬØ©
    0.08
    ively
    0.08
    ãģª
    0.08
    azzi
    0.07
    -leaning
    0.07
    åľ°æĬĬ
    0.07
    /pass
    0.07
    åľ°åIJij
    0.07
    Activations Density 0.006%

    No Known Activations