© 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. 44083
    Prev
    Next
    INDEX
    Explanations

    heat loss and insulation

    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
    解æ¯Ĵ
    -0.10
    icole
    -0.08
    æī«é»ij
    -0.08
    ehme
    -0.07
    æµ·çĩķ
    -0.07
    jong
    -0.07
    èĥ¸çĹĽ
    -0.07
     resolved
    -0.07
    ä¸įæī¿æĭħ
    -0.07
    天ä»Ļ
    -0.07
    POSITIVE LOGITS
    æµģ失
    0.10
    çķĻä½ı
    0.09
     retention
    0.09
    çıįè´µçļĦ
    0.09
     precious
    0.09
    ä¿Ŀä½ı
    0.09
    å®Īä½ı
    0.08
    æĮ½çķĻ
    0.08
    çıįè´µ
    0.08
    裹
    0.08
    Activations Density 0.014%

    No Known Activations