© 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. 27911
    Prev
    Next
    INDEX
    Explanations

    Sharia, courts, judicial, justice

    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
    忱
    -0.07
    ाल
    -0.07
    çĤĬ
    -0.07
    çŃĭèĨľ
    -0.07
    èijĨ
    -0.07
    ä½İè¿·
    -0.07
    çļĦæĪĺçķ¥
    -0.07
     perif
    -0.06
    candidates
    -0.06
     reac
    -0.06
    POSITIVE LOGITS
     justice
    0.12
    åħ¬å¹³åħ¬æŃ£
    0.11
    åħ¬æŃ£
    0.11
    åħ¬å¹³æŃ£ä¹ī
    0.11
    justice
    0.10
    åıĹçIJĨ
    0.10
     punishments
    0.10
    è§ĦåĪĻ
    0.10
     Justice
    0.09
     fairness
    0.09
    Activations Density 0.028%

    No Known Activations