© 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. 21453
    Prev
    Next
    INDEX
    Explanations

    olefin, bond, double bond

    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
    尿裤
    -0.07
    kof
    -0.07
    Outlet
    -0.07
    åħ¨éĿ¢åIJ¯åĬ¨
    -0.07
    交åĪ°
    -0.07
    è§Ħ模åĮĸ
    -0.07
     Natale
    -0.07
    customize
    -0.07
    æķ´æľº
    -0.07
    ä¸ĭè°ĥ
    -0.07
    POSITIVE LOGITS
    ç«ĭä½ĵ
    0.08
     lipat
    0.07
    çī¢åĽº
    0.07
     bond
    0.07
    æĿŁç¼ļ
    0.07
    ffa
    0.07
    å¤ļæĥħ
    0.07
    oller
    0.07
     OPEN
    0.07
    縼
    0.07
    Activations Density 0.001%

    No Known Activations