© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 47437
    Prev
    Next
    INDEX
    Explanations

    negative sentiment when speaking

    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¸įèĥ½æľī
    -0.08
    ä¸į容忽è§Ĩ
    -0.07
    cioni
    -0.07
    ä¸įèĥ½ä½ľä¸º
    -0.07
    assistant
    -0.06
    ä¸įèĥ½ç͍
    -0.06
    ä¸įåı¯å¿½è§Ĩ
    -0.06
    inia
    -0.06
    ipa
    -0.06
    tery
    -0.06
    POSITIVE LOGITS
    æĪĸå°ij
    0.13
    æľīä»»ä½ķ
    0.08
    ä»»ä½ķ
    0.08
    æĽ´ä¸įä¼ļ
    0.08
     سرا
    0.08
    çĿ¬
    0.08
    ä»»ä½ķéĹ®é¢ĺ
    0.08
    èĢĮæĺ¯
    0.08
    iscard
    0.08
    为好
    0.08
    Activations Density 0.204%

    No Known Activations