© 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. 11925
    Prev
    Next
    INDEX
    Explanations

    corruption and negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite

    critical or negative commentary about political corruption, moral decay, or institutional failures.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
    å¯Ľ
    -0.09
    æ¹ĥ
    -0.08
     pleasantly
    -0.08
    ä»»ä½ķåªĴä½ĵ
    -0.08
     discreet
    -0.08
    incontro
    -0.08
     daunting
    -0.07
     appreciated
    -0.07
     mirac
    -0.07
     spontan
    -0.07
    POSITIVE LOGITS
     Worse
    0.15
     worse
    0.13
    缺ä¹ı
    0.11
    è¿ĿèĥĮ
    0.10
    丧失äºĨ
    0.10
     unchecked
    0.10
     ÑħÑĥже
    0.10
     lack
    0.10
    åĬ£è´¨
    0.10
    æģ¶æĢ§
    0.10
    Activations Density 0.349%

    No Known Activations