© 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. 30931
    Prev
    Next
    INDEX
    Explanations

    pathfinding search algorithms

    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
    bauer
    -0.07
     erection
    -0.07
    uchos
    -0.07
    è®¤çľŁåģļ好
    -0.07
    Hosting
    -0.06
    å¤ļä½Ļ
    -0.06
    æ³¥çŁ³
    -0.06
    mula
    -0.06
     resid
    -0.06
    ä½ľåģĩ
    -0.06
    POSITIVE LOGITS
     explores
    0.09
    æݢ索
    0.09
     explored
    0.08
     reachable
    0.08
     Reached
    0.08
     BFS
    0.08
     bfs
    0.08
     íĥIJìĥī
    0.08
    åĪ°è¾¾
    0.08
     explore
    0.08
    Activations Density 0.009%

    No Known Activations