© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58924
    Prev
    Next
    INDEX
    Explanations

    should not

    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
    Negative Logits
    gro
    -0.08
    æłĩåħµ
    -0.07
    åı¨
    -0.07
    ewan
    -0.07
    MethodName
    -0.07
    Ứ
    -0.07
    æĿĤè´§
    -0.07
    è¿ľå¾ģ
    -0.07
    éĢļçĶ¨
    -0.07
    éĢļçĶ¨çļĦ
    -0.07
    POSITIVE LOGITS
     intentionally
    0.15
    æķħæĦı
    0.15
     intentional
    0.14
     purposely
    0.13
    æķħæĦıçļĦ
    0.13
     deliberately
    0.13
    åĪ»æĦı
    0.12
     deliberate
    0.11
    æľīæĦı
    0.10
    ä¸įçł´
    0.10
    Activations Density 0.213%

    No Known Activations