© 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. 58447
    Prev
    Next
    INDEX
    Explanations

    cocaine binding

    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
     SIST
    -0.08
    stech
    -0.08
    æĺłåħ¥
    -0.08
    羣æĬĵå®ŀå¹²
    -0.08
    nach
    -0.08
    å°ıåĬ¨çī©
    -0.07
    ourcem
    -0.07
    emann
    -0.07
    ILLS
    -0.07
    =read
    -0.07
    POSITIVE LOGITS
    æĭīå¾·
    0.06
    æĭĶ
    0.06
    亮
    0.06
    å¸ĥæĸ¯
    0.06
    主人åħ¬
    0.06
    好åij¢
    0.06
    aban
    0.06
    ãģĵãģ¨ãģ«
    0.06
    åıijæĮ¥
    0.06
    loit
    0.06
    Activations Density 0.102%

    No Known Activations