© 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. 46449
    Prev
    Next
    INDEX
    Explanations

    social responsibility and change

    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
    Ù°
    -0.07
    ento
    -0.06
    åŃ©
    -0.06
     comunque
    -0.06
    /
    -0.06
    anger
    -0.05
    åħ¹
    -0.05
    æ²³ä¸ľ
    -0.05
     softly
    -0.05
    inet
    -0.05
    POSITIVE LOGITS
    éħĴå±ĭ
    0.09
    åħ¥å¾®
    0.09
    è·¯éĢı
    0.08
    çĶļèĩ³æĺ¯
    0.08
    å¨ģ士
    0.08
    æĹłè®ºæĺ¯åľ¨
    0.08
    æĺ¯ä¸Ģ个人
    0.08
    åįķä½įåıĤåĬł
    0.08
    æĪIJ份
    0.08
    agine
    0.07
    Activations Density 0.017%

    No Known Activations