© 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. 26901
    Prev
    Next
    INDEX
    Explanations

    investor-state disputes privatization capitalist US companies

    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
     ocas
    -0.07
    ç«ĭå¿Ĺ
    -0.07
    ä½İä½į
    -0.07
    å®ķ
    -0.07
    è¯ļå¿ĥ
    -0.07
    siz
    -0.06
    éĶĻé¢ĺ
    -0.06
     اÙĦإطÙĦاÙĤ
    -0.06
     Mannheim
    -0.06
    ernel
    -0.06
    POSITIVE LOGITS
     neoliberal
    0.12
    åŀĦæĸŃ
    0.10
     disproportionately
    0.09
     heg
    0.09
    强åĬ¿
    0.09
    è¿İåIJĪ
    0.09
     capitalist
    0.09
    åıĺ缸
    0.09
     questionable
    0.09
    åªļ
    0.09
    Activations Density 0.871%

    No Known Activations