© 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. 21663
    Prev
    Next
    INDEX
    Explanations

    tall structures like towers and lighthouses

    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
    éĵºå¼Ģ
    -0.08
    æ°´åĮº
    -0.08
    atak
    -0.07
    æ·Ĩ
    -0.07
    éĵº
    -0.07
     boxed
    -0.07
    涧
    -0.07
    å°ı溪
    -0.07
     pooled
    -0.07
    æŃ£è½¨
    -0.07
    POSITIVE LOGITS
    çŁĹ
    0.12
     towers
    0.11
     erected
    0.11
    å±¹ç«ĭ
    0.11
     tower
    0.11
    æŀĹç«ĭ
    0.10
    顶端
    0.10
    é«ĺèĢ¸
    0.10
    å¡Ķ
    0.10
     tallest
    0.10
    Activations Density 0.127%

    No Known Activations