© 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. 60162
    Prev
    Next
    INDEX
    Explanations

    illegal immigrant status

    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
    ertest
    -0.08
    çıĤ
    -0.08
    byt
    -0.07
    è´´è¿ij
    -0.07
    olf
    -0.07
    ivy
    -0.07
     magn
    -0.07
    ä¸į失
    -0.07
    efs
    -0.07
     дово
    -0.06
    POSITIVE LOGITS
     unauthorized
    0.11
     unlawful
    0.11
     illeg
    0.11
     improperly
    0.10
     unlaw
    0.10
    æĪĸæľª
    0.10
     improper
    0.10
     illegally
    0.10
    åIJĪæ³ķ
    0.10
     lawful
    0.10
    Activations Density 0.064%

    No Known Activations