© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50143
    Prev
    Next
    INDEX
    Explanations

    path of/from/between

    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
    æŃ£åĢ¼
    -0.07
    绣ä¸ĢçļĦ
    -0.07
    åĢ¤
    -0.07
     values
    -0.07
    ç«ŀçĮľ
    -0.07
     zet
    -0.07
    anlage
    -0.07
    éĩijçļĦ
    -0.07
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.06
    reeze
    -0.06
    POSITIVE LOGITS
     paths
    0.14
    è·¯å¾Ħ
    0.13
     Paths
    0.13
     path
    0.11
     shortest
    0.11
    æľĢçŁŃ
    0.11
    paths
    0.11
    path
    0.11
     Path
    0.10
     routes
    0.10
    Activations Density 0.018%

    No Known Activations