© 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. 14789
    Prev
    Next
    INDEX
    Explanations

    kill parents, awareness, consequence

    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
    请ç«ĭåį³
    -0.07
    贤纳士
    -0.07
     hoss
    -0.07
    gon
    -0.06
    ëĿ¼ëıĦ
    -0.06
    è¾ĥçŁŃ
    -0.06
     âĤ¬*
    -0.06
    (APP
    -0.06
     infamous
    -0.06
    æ¬
    -0.06
    POSITIVE LOGITS
    æ¯Ķ以åīį
    0.08
    è¿Ļä¹Ī好
    0.08
    è¿Ļä¹Īå¤ļ
    0.08
    ç§įç§į
    0.08
    è¿ĻäºĽä¸ľè¥¿
    0.08
    ÑĢÑĭз
    0.07
    æĸ¹æĸ¹éĿ¢
    0.07
    æĩĤå¾Ĺ
    0.07
    å±Ģå±Ģéķ¿
    0.07
    çļĦåģļæ³ķ
    0.07
    Activations Density 0.003%

    No Known Activations