© 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. 32210
    Prev
    Next
    INDEX
    Explanations

    "happy together", "want a"

    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
    æŁIJäºĽ
    -0.07
    åħ·æľīä¸Ģå®ļ
    -0.07
     generator
    -0.07
    åħ·æľīä¸Ģå®ļçļĦ
    -0.07
    uas
    -0.07
    æŁIJç§į
    -0.06
    ä¹Łæľīä¸Ģå®ļçļĦ
    -0.06
    ëģ¼
    -0.06
    å¥Ĺ
    -0.06
    olume
    -0.06
    POSITIVE LOGITS
     demonstr
    0.08
    otify
    0.07
    vida
    0.07
    å§ĭèĩ³
    0.07
    管çļĦ
    0.07
    æģ°æģ°
    0.07
    otel
    0.07
    å°±æĺ¯äºĨ
    0.07
    åħļçļĦäºĮåįģ大
    0.07
    åħ³æĿij
    0.07
    Activations Density 0.003%

    No Known Activations