© 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. 34506
    Prev
    Next
    INDEX
    Explanations

    Mars, surface features, craters, poles

    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
    æ³³
    -0.07
    å¾Ļ
    -0.07
     pesc
    -0.07
    è¯ļ
    -0.07
     Excel
    -0.07
    æ°´ä¸ŃçļĦ
    -0.07
    ension
    -0.06
    thread
    -0.06
    游泳
    -0.06
     train
    -0.06
    POSITIVE LOGITS
     crater
    0.13
     depress
    0.09
     crust
    0.09
     surface
    0.09
    ä¸ĢèĦļ
    0.09
     rover
    0.08
     glac
    0.08
    agl
    0.08
    ìŀĶ
    0.08
     glaciers
    0.08
    Activations Density 0.041%

    No Known Activations