© 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. 25736
    Prev
    Next
    INDEX
    Explanations

    dissolved air, gases, oxygen

    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
     pans
    -0.07
     vote
    -0.07
    çĥ½çģ«
    -0.06
    ÅĻej
    -0.06
     pixel
    -0.06
    çĥ¨
    -0.06
    åĥıç´ł
    -0.06
    ç½ijç«Ļåľ°åĽ¾
    -0.06
    è¶Ĭèµ°è¶Ĭ
    -0.06
    羶
    -0.06
    POSITIVE LOGITS
    blas
    0.09
    æ°´éĩĮ
    0.09
    æ°´ä¸Ń
    0.09
     uptake
    0.08
    æ°´ä½ĵ
    0.08
     gases
    0.08
    ä¸Ĭæµ®
    0.08
    çļĦæĸ°é²ľ
    0.08
    æ°´è´¨
    0.08
    ä¸įæķ£
    0.08
    Activations Density 0.020%

    No Known Activations