© 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. 32673
    Prev
    Next
    INDEX
    Explanations

    river crossings and bridges

    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
    è§ĴèIJ½éĩĮ
    -0.08
    è§ĴèIJ½
    -0.08
    æĸ¯é¡¿
    -0.08
    ãĥĢãĤ¦ãĥ³
    -0.07
    çIJĥçļĦ
    -0.07
    Corner
    -0.07
     hierarchy
    -0.07
    çŃĴ
    -0.07
    greg
    -0.07
    æĮģä»ĵ
    -0.07
    POSITIVE LOGITS
     crossings
    0.13
     crossing
    0.13
     bridge
    0.12
     ê±´ëĦĪ
    0.12
    横跨
    0.12
    è·¨è¶Ĭ
    0.12
    æ¡¥
    0.11
     bridges
    0.11
    è·¨
    0.11
    è·¨è¿ĩ
    0.11
    Activations Density 0.114%

    No Known Activations