© 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. 64299
    Prev
    Next
    INDEX
    Explanations

    intentional harm or disruption

    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
     trag
    -0.07
    éĢıè¿ĩ
    -0.07
    åºĶéħ¬
    -0.07
    å¥¢æľĽ
    -0.07
    é¢Ħä¹ł
    -0.07
    _exempt
    -0.07
    HOT
    -0.06
     ìĿ´ìĥģìĿ´
    -0.06
    alia
    -0.06
    御
    -0.06
    POSITIVE LOGITS
    æķħæĦı
    0.15
     deliberately
    0.14
    æķħæĦıçļĦ
    0.13
     intentionally
    0.12
    ãĤıãģĸ
    0.11
     purposely
    0.11
    åĪ¶éĢłçļĦ
    0.10
     sabot
    0.10
    æĪĸåĪ©çĶ¨
    0.10
     nhằm
    0.10
    Activations Density 0.188%

    No Known Activations