© 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. 43211
    Prev
    Next
    INDEX
    Explanations

    shapes, logo, vector, server, UIView, icket, heat

    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
    ');</
    -0.07
    oom
    -0.06
    gt
    -0.06
    agan
    -0.06
    æĬĸæĵŀ
    -0.06
    ISO
    -0.06
     হয়à§ĩ
    -0.06
     Joaquim
    -0.06
    abo
    -0.06
    reira
    -0.06
    POSITIVE LOGITS
    精工
    0.08
    åģļåĪ°çļĦ
    0.07
    å®ĩ
    0.07
    为èį£
    0.07
    çĽ¸çŁ¥
    0.07
    åıŃ
    0.07
    èģĶ社
    0.07
    _CHOICES
    0.07
    鼷æĸ¯
    0.07
     panne
    0.07
    Activations Density 0.048%

    No Known Activations