© 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. 29584
    Prev
    Next
    INDEX
    Explanations

    unlawfully, illegal, prohibited, forbidden

    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
     conserv
    -0.07
    Õ¡Õ£
    -0.07
    æĹłæļĩ
    -0.07
    anon
    -0.07
    æĩĴå¾Ĺ
    -0.07
    ä¸įè¦ģéĶĻè¿ĩ
    -0.07
    openh
    -0.07
    åŁĥ
    -0.06
     pleasantly
    -0.06
    çħ§é¡¾å¥½
    -0.06
    POSITIVE LOGITS
    ä»»ä½ķå½¢å¼ıçļĦ
    0.13
    以任ä½ķ
    0.12
     unlaw
    0.12
     prohibited
    0.12
    ç§ģèĩª
    0.12
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    0.11
    ä¼ģåĽ¾
    0.11
     improperly
    0.11
     forbidden
    0.11
    è¿ĿåıįäºĨ
    0.11
    Activations Density 0.110%

    No Known Activations