© 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. 28546
    Prev
    Next
    INDEX
    Explanations

    plant species

    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
    ÙĩÙĨ
    -0.08
    è¿Ľä¸ĢæŃ¥
    -0.08
     furthermore
    -0.07
    \n
    -0.07
    \/
    -0.07
    sequently
    -0.06
     firstly
    -0.06
    è¾ĥ为
    -0.06
     proceeding
    -0.06
    å±ħçĦ¶
    -0.06
    POSITIVE LOGITS
    ä¸ĭä¸Ģç«ł
    0.09
    æľĢæĸ°ç«łèĬĤ
    0.08
    tiny
    0.08
    æľĢåīį沿
    0.08
    第äºĮç«ł
    0.07
    ãģłãģ£ãģ¦
    0.07
    usza
    0.07
    ÃģC
    0.07
    —from
    0.07
    chai
    0.07
    Activations Density 0.001%

    No Known Activations