© 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. 13753
    Prev
    Next
    INDEX
    Explanations

    punctuation and non-English characters

    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
    çļĦ详ç»Ĩ
    -0.09
    详ç»Ĩä»ĭç»įäºĨ
    -0.07
     correctement
    -0.07
    ä¸įå®ļæľŁ
    -0.07
    ãģ®è©³ç´°
    -0.07
    Complex
    -0.07
    ãĤ¶ãĥ¼
    -0.07
    ä¹Łåıªæĺ¯
    -0.07
     übrigens
    -0.07
     Complex
    -0.07
    POSITIVE LOGITS
    èģĶæĥ³åĪ°
    0.09
    æĥ³åĪ°äºĨ
    0.09
     brainstorm
    0.08
    寻æī¾
    0.08
    æĹ¢çĦ¶æĺ¯
    0.08
     hinted
    0.08
    æĥ³åĪ°
    0.08
     obvious
    0.08
    æĥ³åĪ°çļĦ
    0.08
    æĢĿèĢĥ
    0.08
    Activations Density 0.118%

    No Known Activations