© 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. 32970
    Prev
    Next
    INDEX
    Explanations

    narrative manipulation

    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
    æĬ¥åijĬæľŁ
    -0.09
    åĪ°å²Ĺ
    -0.08
    æľĭåıĭçļĦ
    -0.08
    ĩ´
    -0.08
     sahab
    -0.07
    åı¤å±ĭ
    -0.07
    idd
    -0.07
    æĺ¯åĽł
    -0.07
    éĢļ讯å½ķ
    -0.07
     sized
    -0.07
    POSITIVE LOGITS
    è¯Ŀè¯ŃæĿĥ
    0.11
    å¤±çľŁ
    0.10
     narratives
    0.10
    主导
    0.10
     dominant
    0.10
    解éĩĬæĿĥ
    0.09
     official
    0.09
    çļĦè¯Ŀè¯Ń
    0.09
    å®ĺæĸ¹
    0.09
    篡æĶ¹
    0.09
    Activations Density 0.066%

    No Known Activations