© 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. 41046
    Prev
    Next
    INDEX
    Explanations

    hostile entities and conflict

    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
    pend
    -0.07
    å±ī
    -0.06
     Cay
    -0.06
    æĬĵå®ŀ
    -0.06
    anken
    -0.06
    ç½ļ
    -0.06
    è¾Ľ
    -0.06
     Grü
    -0.06
    代ä¹ĭ
    -0.06
    尼奥
    -0.06
    POSITIVE LOGITS
     threats
    0.11
    åı¯æģ¶
    0.11
    æģ¶åĬ¿åĬĽ
    0.10
     hostile
    0.10
    åĬ¿åĬĽçļĦ
    0.10
     threat
    0.10
     threatening
    0.10
    å¨ģèĥģ
    0.09
    æģ¶æĦı
    0.09
     Threat
    0.09
    Activations Density 0.325%

    No Known Activations