© 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. 10672
    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
    èĽĩ
    -0.08
    å¦ĤæĦı
    -0.07
    fen
    -0.06
    çģĺ
    -0.06
    ä¸įåĩĨ
    -0.06
    vad
    -0.06
    agin
    -0.06
     vs
    -0.06
    èĩªåľ¨
    -0.06
    пин
    -0.06
    POSITIVE LOGITS
    ehme
    0.08
    Õ¡Öģ
    0.07
    ãĥķãĤ©ãĥŃãĥ¼
    0.07
    ORMAT
    0.07
    á»ķ
    0.07
    ç¼Ī
    0.07
    ç´¯çļĦ
    0.07
    ä»Ģä¹Īäºĭæĥħ
    0.07
     pell
    0.07
    ç´¯äºĨ
    0.07
    Activations Density 0.000%

    No Known Activations