© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33153
    Prev
    Next
    INDEX
    Explanations

    formation of bubbles or obstructions

    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
    alani
    -0.08
    ulli
    -0.07
    æ¥Ķ
    -0.07
    ä½Ĩåĩ¡
    -0.07
    çĭĤå¦Ħ
    -0.07
    åĴĮæĶ¹åĸĦ
    -0.07
    iegel
    -0.07
    çݯ线
    -0.07
    Implemented
    -0.06
    death
    -0.06
    POSITIVE LOGITS
    ä¸įåĪ©äºİ
    0.10
    ãģĽãģ£ãģĭãģı
    0.10
    æĹłæ³ķæŃ£å¸¸
    0.09
    å°ĨæĹłæ³ķ
    0.09
     hind
    0.09
     undermines
    0.09
    èĢĮæĹłæ³ķ
    0.09
     prematurely
    0.09
    å°±æĹłæ³ķ
    0.08
    zac
    0.08
    Activations Density 0.093%

    No Known Activations