© 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. 34347
    Prev
    Next
    INDEX
    Explanations

    threaten or oppose

    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
    èµĦ讯ç½ij
    -0.08
    zien
    -0.07
    è¿ĺæĺ¯ä¸įéĶĻçļĦ
    -0.07
     overlooking
    -0.07
    ä¸į缺
    -0.07
    èĶ¼
    -0.07
    ä¸įèĩ³
    -0.07
    umpa
    -0.07
     soucis
    -0.07
    undry
    -0.07
    POSITIVE LOGITS
     perceived
    0.09
    被è§Ĩ为
    0.09
    ä¼ļå¼ķèµ·
    0.09
     dianggap
    0.08
    ç¢į
    0.08
    ä»ĸ们认为
    0.08
    太好
    0.08
    activ
    0.08
    ä¸į符åIJĪ
    0.08
     too
    0.07
    Activations Density 0.342%

    No Known Activations