© 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. 28882
    Prev
    Next
    INDEX
    Explanations

    quitting habits and seeking recovery

    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
    å¤ļæīį
    -0.07
    缼åĨµ
    -0.07
    ä½łæĺ¯æĪijçļĦ
    -0.07
    æİĪäºĪ
    -0.07
    æĤłéĹ²
    -0.07
    å°ıè§ij
    -0.07
     prolung
    -0.07
    æ·¡å®ļ
    -0.07
     unfairly
    -0.06
    精巧
    -0.06
    POSITIVE LOGITS
    æĶ¹æŃ£
    0.14
    æĶ¹åıĺçļĦ
    0.13
    æĤĶæĶ¹
    0.13
     repent
    0.11
    幡
    0.11
    æĶ¹åıĺ
    0.11
    æĶ¹åĸĦ
    0.11
    æĶ¹äºĨ
    0.10
    åIJijåĸĦ
    0.10
    åıįçľģ
    0.10
    Activations Density 0.114%

    No Known Activations