© 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. 56563
    Prev
    Next
    INDEX
    Explanations

    spatial or hydrophobic

    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
    elm
    -0.07
    -Sah
    -0.06
    é»Ħé¾Ļ
    -0.06
    änge
    -0.06
    TypeEnum
    -0.06
    esy
    -0.06
     biochemical
    -0.06
     dort
    -0.06
    æĪijçļĦç¥Ŀç¦ı
    -0.06
    ä½ıæ°ij
    -0.06
    POSITIVE LOGITS
     spatial
    0.09
     Spatial
    0.08
    Spatial
    0.08
    ัà¹Īà¸ĩ
    0.07
    igr
    0.07
    æľĪä¸Ĭ
    0.07
    æĹ¥æ´»åĬ¨
    0.07
    .spatial
    0.07
    ยà¹Į
    0.07
     Horiz
    0.07
    Activations Density 0.761%

    No Known Activations