© 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. 28550
    Prev
    Next
    INDEX
    Explanations

    water chemistry, recycle gas, heat exchangers

    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
    å¾Ĵæīĭ
    -0.08
    (Constructor
    -0.07
     rooted
    -0.07
    ä¹Ķ
    -0.06
    adic
    -0.06
    ä¸į计
    -0.06
    åĩºåĢŁ
    -0.06
     Potenz
    -0.06
    æĹłæĦ§
    -0.06
    åĪ¶åĵģåİĤ
    -0.06
    POSITIVE LOGITS
    æݧåĪ¶å¥½
    0.11
    æĵįä½ľè§Ħç¨ĭ
    0.10
    /feed
    0.10
    -feed
    0.09
    ç»´æĮģ
    0.09
    å·¥åĨµ
    0.09
     feed
    0.09
     Feed
    0.09
     downstream
    0.09
    ç»´æĮģåľ¨
    0.09
    Activations Density 0.048%

    No Known Activations