© 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. 40400
    Prev
    Next
    INDEX
    Explanations

    ligands, carbenes, or 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
     Hubb
    -0.07
     dens
    -0.07
    yks
    -0.07
    æħ§
    -0.07
    å¾Īè¾Ľèĭ¦
    -0.06
    åĪ©äºļ
    -0.06
    stro
    -0.06
    åĮ»åѦè§Ĥå¯Ł
    -0.06
    fullscreen
    -0.06
     skyl
    -0.06
    POSITIVE LOGITS
    离åİ»
    0.11
    toh
    0.08
    æŀģ好çļĦ
    0.07
    æį¢æĪIJ
    0.07
    /tiny
    0.07
    ç»ĻåĬĽ
    0.07
    åĪ©çī©
    0.07
    elius
    0.07
    åħ·å¤ĩèī¯å¥½çļĦ
    0.07
    atra
    0.07
    Activations Density 0.008%

    No Known Activations