© 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. 40175
    Prev
    Next
    INDEX
    Explanations

    socioeconomic status and inequalities

    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
    ä¸Ĭæŀ¶
    -0.09
     onboard
    -0.07
    hode
    -0.07
    ì§ĢìĤ¬
    -0.07
    å®īåħ¨ç¬¬ä¸Ģ
    -0.07
    egel
    -0.07
    客æĪ·éľĢæ±Ĥ
    -0.07
    ä¸ļåĬ¡åıijå±ķ
    -0.07
    emplate
    -0.06
    èij©
    -0.06
    POSITIVE LOGITS
     socioeconomic
    0.12
     socio
    0.09
     access
    0.09
     poorer
    0.09
     strat
    0.08
     бед
    0.08
    åıĹæķĻèĤ²
    0.08
    æľīéĴ±
    0.08
    è´«åĽ°
    0.08
    Access
    0.08
    Activations Density 0.060%

    No Known Activations