© 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. 14026
    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
    agnes
    -0.08
    infeld
    -0.07
    ezu
    -0.07
    essen
    -0.07
    _accessor
    -0.07
    èijµèĬ±
    -0.07
    wach
    -0.07
     Velo
    -0.07
    ì»
    -0.07
    erein
    -0.07
    POSITIVE LOGITS
    继ç»Ńåħ³æ³¨
    0.07
    ç¿»äºĨ
    0.07
    ubber
    0.07
    带æĪijåİ»
    0.06
    èĥ½åIJĥèĭ¦èĢIJåĬ³
    0.06
    æĿĥçļĦ
    0.06
    ä¸Ģæĸ°
    0.06
    ä¸įæĢ¥
    0.06
    ired
    0.06
    disabled
    0.06
    Activations Density 0.000%

    No Known Activations