© 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. 61679
    Prev
    Next
    INDEX
    Explanations

    seamless, concrete, casing, tubulars

    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¸IJ
    -0.07
    Rap
    -0.07
    à¹Ģล
    -0.07
    å½ķ
    -0.07
    rap
    -0.07
     rap
    -0.07
    çģ°å°ĺ
    -0.07
    æįº
    -0.06
    è·µ
    -0.06
    åħļåĴĮ人æ°ij
    -0.06
    POSITIVE LOGITS
    å£ģåİļ
    0.09
    é¼ĵèµ·
    0.09
    é¼ĵ
    0.09
    åİĭåĬĽå®¹åĻ¨
    0.09
    åĨħå¤ĸ
    0.09
    åĨħå£ģ
    0.09
     hoop
    0.08
    åĨħ侧
    0.08
    æī¿åıĹ
    0.08
    å·¥ä½ľåİĭåĬĽ
    0.08
    Activations Density 0.004%

    No Known Activations