© 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. 41647
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    esch
    -0.07
    åłº
    -0.07
     Niem
    -0.07
    ä¸įå¤ļçļĦ
    -0.07
    ä¸Ĭ大
    -0.06
    ÙĨدÙĨ
    -0.06
    人åķĬ
    -0.06
    u
    -0.06
    æīī
    -0.06
    åī¥
    -0.06
    POSITIVE LOGITS
    ä¹Ŀ天
    0.08
    èµĦéĩijæĬķåħ¥
    0.07
    åħ¶è§ĤçĤ¹
    0.06
    è§ĤçĤ¹
    0.06
    åħ·ä½ĵ
    0.06
    ahl
    0.06
    èĩªå·±åģļ
    0.06
    æŀģåĬĽ
    0.06
    ãģĬãĤĪãģ³
    0.06
     acu
    0.06
    Activations Density 0.000%

    No Known Activations