© 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. 16866
    Prev
    Next
    INDEX
    Explanations

    ultraviolet, pharmaceutically, irradiation

    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
    æĢĴ
    -0.08
    è£ħæľº
    -0.07
    æľĿ天
    -0.07
    liz
    -0.07
    CEL
    -0.07
    iez
    -0.07
    ä¸ĩ
    -0.07
    inat
    -0.07
    çŁŃæĸĩ
    -0.07
    eld
    -0.06
    POSITIVE LOGITS
    éĢļè¿ĩåIJİ
    0.09
    éĢļè¿ĩè¿Ļ个
    0.09
    ç»ıçĶ±
    0.08
    through
    0.08
     ultimately
    0.08
     thru
    0.08
    éĢļè¿ĩç½ij绾
    0.08
    éĢļè¿ĩ对
    0.08
     Through
    0.07
     through
    0.07
    Activations Density 0.350%

    No Known Activations