© 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. 31550
    Prev
    Next
    INDEX
    Explanations

    meteorite impacts and craters

    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
    鸥
    -0.08
    è¿ĻéĹ´
    -0.07
    ighthouse
    -0.06
    åĮħ袱
    -0.06
    ÑĤок
    -0.06
     Aquarium
    -0.06
     enferm
    -0.06
    леб
    -0.06
    trend
    -0.06
    healthy
    -0.06
    POSITIVE LOGITS
    æĴŀåĩ»
    0.10
     debris
    0.10
     crater
    0.10
    æįŁæ¯ģ
    0.09
    æ¯ģçģŃ
    0.09
     fragments
    0.09
     surviv
    0.09
    åľŁçŁ³
    0.08
    çģ«
    0.08
    bris
    0.08
    Activations Density 0.023%

    No Known Activations