© 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. 24784
    Prev
    Next
    INDEX
    Explanations

    benzene, BPA, compounds, drug, heavy metals, vitamin

    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
    è¿ĻäºĽåľ°æĸ¹
    -0.06
    æļĩ
    -0.06
    ç«£
    -0.06
     tw
    -0.06
    é²
    -0.06
    ãģİ
    -0.06
    å»¶è¿Ł
    -0.06
    æľºæŀĦåĴĮ
    -0.06
    Scope
    -0.06
    èĵ¬
    -0.05
    POSITIVE LOGITS
    åľ¨åIJĦ
    0.09
    äºİè¡Į
    0.09
    åŃĺåľ¨äºİ
    0.09
    :absolute
    0.09
    æĢ»éĩı
    0.09
    æĢ»éĩıçļĦ
    0.08
    æµĵ度çļĦ
    0.08
    è¡ĢçĹĩ
    0.08
    å¾·åŁº
    0.08
    ç«¥åŃIJ
    0.08
    Activations Density 0.192%

    No Known Activations