© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27112
    Prev
    Next
    INDEX
    Explanations

    bad, wrong, sin, illegal, racist

    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
    ãģ¨ãģĨ
    -0.08
    вÑĭв
    -0.07
     mirac
    -0.07
     weakest
    -0.07
    èĪĮ
    -0.07
    aily
    -0.07
    æĺ¯æľĢéĩįè¦ģçļĦ
    -0.07
    åIJĦ项è§Ħç«łåĪ¶åº¦
    -0.07
    å¹´æĺ¥èĬĤ
    -0.07
    çļĦå¿ĥæĢĿ
    -0.07
    POSITIVE LOGITS
    åĽłä¸ºè¿Ļ
    0.11
    åĽłä¸ºå®ĥ
    0.08
     tersendiri
    0.08
     frowned
    0.08
     punishable
    0.08
    çĶļèĩ³æĺ¯
    0.07
    è¿Ļç§įè¡Į为
    0.07
    isha
    0.07
     because
    0.07
     acceptable
    0.07
    Activations Density 0.124%

    No Known Activations