© 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. 31928
    Prev
    Next
    INDEX
    Explanations

    pain and suffering

    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
    verbind
    -0.08
     سازÛĮ
    -0.08
    ellar
    -0.08
    quiv
    -0.08
    idual
    -0.08
    avern
    -0.07
    ?url
    -0.07
     defic
    -0.07
    ãĤ·ãĤ¢
    -0.07
     semula
    -0.07
    POSITIVE LOGITS
     endured
    0.11
     inflicted
    0.10
    æĬĺ磨
    0.09
    çĹĽèĭ¦
    0.09
    ä¸įåłª
    0.09
     pain
    0.08
     Pain
    0.08
    磨éļ¾
    0.08
    èĭ¦çļĦ
    0.08
     ordeal
    0.08
    Activations Density 0.066%

    No Known Activations