© 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. 30293
    Prev
    Next
    INDEX
    Explanations

    persuasion techniques and effectiveness

    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
    ä¿ĿæĬ¤èĩªå·±
    -0.08
    ç»Ļèĩªå·±
    -0.08
    Disallow
    -0.07
    etit
    -0.07
    ä¹īåĭĩ为
    -0.07
     Liberties
    -0.07
    åħīèį£
    -0.07
    ริà¸Ķ
    -0.07
    給èĩªå·±
    -0.07
    napshot
    -0.07
    POSITIVE LOGITS
    诱导
    0.13
    åĪºæ¿Ģ
    0.13
     persu
    0.12
     persuasion
    0.12
     elic
    0.12
     effectiveness
    0.12
    诱
    0.12
    æĦŁåı¬
    0.11
    è°ĥåĬ¨
    0.11
     persuasive
    0.11
    Activations Density 0.192%

    No Known Activations