© 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. 64116
    Prev
    Next
    INDEX
    Explanations

    suffix of words

    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
     other
    -0.06
    æĪijåĴĮæĪijçļĦ
    -0.06
    羣æŃ£
    -0.06
    ccio
    -0.06
    ıs
    -0.06
    è¾¹ç¼ĺ
    -0.06
    ACC
    -0.05
    astia
    -0.05
    æķĻèĤ²çļĦ
    -0.05
     only
    -0.05
    POSITIVE LOGITS
    ëĤĺë§Ī
    0.10
    çĶļèĩ³æľīäºĽ
    0.10
    wijs
    0.09
    ãģĭãģ¤
    0.09
    ä½Ĩèĩ³å°ij
    0.09
    æŶéĹ´éĩĮ
    0.09
    åĴĮæľĢ
    0.08
    jec
    0.08
    æĪĸèĢħ说
    0.08
     ترÛĮÙĨ
    0.08
    Activations Density 0.239%

    No Known Activations