© 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. 4231
    Prev
    Next
    INDEX
    Explanations

    ego, worldly, personal gain

    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
    elsing
    -0.07
     silenc
    -0.07
    llib
    -0.07
    loquent
    -0.07
    çIJħ
    -0.06
     اÙĦÙĥب
    -0.06
    å¹´éĿĴ
    -0.06
    Dll
    -0.06
    weg
    -0.06
     pars
    -0.06
    POSITIVE LOGITS
    ä¸İä»ĸ人
    0.09
    å¾Ĺ失
    0.08
     worldly
    0.07
    гни
    0.07
    欲
    0.07
    为ä»ĸ人
    0.07
    pus
    0.07
    为èĩªå·±
    0.07
     ego
    0.07
    æ»ĭ
    0.07
    Activations Density 0.034%

    No Known Activations