© 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. 1443
    Prev
    Next
    INDEX
    Explanations

    discriminating on basis; unfair treatment

    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
    缨
    -0.09
    readcrumbs
    -0.08
    ØŃÙĦØ©
    -0.07
    eturn
    -0.07
    éĹ®åĮ»çĶŁ
    -0.07
     spender
    -0.07
    usercontent
    -0.07
    วิà¸ģฤ
    -0.07
    urus
    -0.07
     overrun
    -0.07
    POSITIVE LOGITS
     discriminatory
    0.16
    æѧè§Ĩ
    0.15
     discrimination
    0.14
     racially
    0.13
     Discrim
    0.13
     discriminate
    0.13
    ä¸įåħ¬å¹³
    0.12
     unfair
    0.12
     discriminator
    0.11
     ì°¨ë³Ħ
    0.11
    Activations Density 0.084%

    No Known Activations