© 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. 51638
    Prev
    Next
    INDEX
    Explanations

    financial crisis and bailouts

    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
     COPYRIGHT
    -0.08
    æľĢç»ĪåıĹçĽĬ
    -0.07
    æĭĽå·¥
    -0.07
    ä¼ģä¸ļåıĹçĽĬ
    -0.07
    å¾ģåľ°
    -0.07
    å°ijèµ°
    -0.07
     изда
    -0.07
    çĸ¼çĹĽ
    -0.07
    ç«ŀåĵģ
    -0.07
    交åıīè·¯åı£
    -0.07
    POSITIVE LOGITS
     Aggregate
    0.09
     holdings
    0.09
     liquidity
    0.09
     Tier
    0.08
    æµģåĬ¨æĢ§
    0.08
    è§Ħ模
    0.08
     aggregate
    0.08
     bailout
    0.08
     tier
    0.07
    Aggregate
    0.07
    Activations Density 0.076%

    No Known Activations