© 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. 22612
    Prev
    Next
    INDEX
    Explanations

    formal or serious tone

    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
     intuitive
    -0.10
    åįģä¸ĥç«ł
    -0.09
    å¿«ä¹IJçļĦ
    -0.09
     Muhamm
    -0.08
    egd
    -0.08
    ç®Ģåįķæĺĵ
    -0.08
    parg
    -0.08
    çĹĽå¿«
    -0.08
     intuit
    -0.08
    Ñģполни
    -0.08
    POSITIVE LOGITS
     formal
    0.12
    严èĤĥ
    0.11
    ä¸įèĭŁ
    0.11
    åºĦéĩį
    0.11
    åħ¸éĽħ
    0.11
    æŃ£å¼ı
    0.11
    严谨
    0.10
    æŃ£å¼ıçļĦ
    0.10
    åļ´
    0.10
     solemn
    0.10
    Activations Density 0.073%

    No Known Activations