© 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. 31802
    Prev
    Next
    INDEX
    Explanations

    labor class struggle oppression

    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
    éģĵè¿ľ
    -0.10
    ĮĢ
    -0.08
    -inline
    -0.08
    alet
    -0.08
     psycholog
    -0.08
    leta
    -0.08
    ülen
    -0.08
    <quote
    -0.08
    å°½æľī
    -0.08
    incs
    -0.08
    POSITIVE LOGITS
    éĺ¶çº§
    0.10
    éĺ¶çº§çļĦ
    0.10
    åī¥åīĬ
    0.07
    æĸĹäºī
    0.07
    åĬ³åĬ¨
    0.07
    ÙĪبÙĬ
    0.07
     proletariat
    0.07
     solidarity
    0.07
    ä¸Ĭå±Ĥ
    0.07
     Chatt
    0.06
    Activations Density 0.004%

    No Known Activations