© 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. 56481
    Prev
    Next
    INDEX
    Explanations

    C-H, C-N, C-C bonds

    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
    éĢĨæµģ
    -0.07
    iaux
    -0.07
    æĸ¹æŃ£
    -0.07
    éĽĨæķ£
    -0.06
    å®ĪåĢĻ
    -0.06
    漪
    -0.06
    ospace
    -0.06
    shade
    -0.06
    åħľ
    -0.06
    omagnet
    -0.06
    POSITIVE LOGITS
     bonds
    0.10
     bond
    0.09
     Bond
    0.09
     Bonds
    0.08
    Bond
    0.08
    Ñģел
    0.08
    è¿ŀæİ¥çļĦ
    0.08
    夫妻åħ³ç³»
    0.08
     bonded
    0.08
    yles
    0.08
    Activations Density 0.013%

    No Known Activations