© 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. 40880
    Prev
    Next
    INDEX
    Explanations

    positive sentiment

    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
    ä½İ级
    -0.08
    æŀģ端
    -0.07
    åİĮæģ¶
    -0.07
    åĺ²è®½
    -0.07
    åĵ¥ä»¬
    -0.07
    侮辱
    -0.07
    æŃ»äºİ
    -0.07
    åĨ·ç¬ij
    -0.07
     incompetent
    -0.07
     sloppy
    -0.07
    POSITIVE LOGITS
     pandemi
    0.08
     Afgan
    0.08
    æľīæĿĥä¿ĿçķĻ
    0.08
    æľªå°½
    0.08
    ðŁĺĬ
    0.08
    åľŁèĢ³
    0.07
     inspir
    0.07
     thoughtful
    0.07
    æ¯ĵ
    0.07
     heartfelt
    0.07
    Activations Density 2.383%

    No Known Activations