© 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. 41764
    Prev
    Next
    INDEX
    Explanations

    polymer, chain, reaction, distance, familial

    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
    anced
    -0.08
    ikan
    -0.08
    åºŀ
    -0.07
    èķĬ
    -0.07
    èĩ£
    -0.07
    ancers
    -0.06
    åºĦéķĩ
    -0.06
     capt
    -0.06
    iru
    -0.06
    RR
    -0.06
    POSITIVE LOGITS
    çĥŃéŨæݨèįIJ
    0.11
    çī¹åĪ«æĺ¯
    0.09
    èĢĮä¸Ķæĺ¯
    0.08
    å°¤åħ¶æĺ¯
    0.08
    zw
    0.08
    çīĪæĿĥå±ŀäºİ
    0.08
    è¶Ĭæĺ¯
    0.07
    عار
    0.07
    itiv
    0.07
    ippi
    0.07
    Activations Density 0.482%

    No Known Activations