© 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. 46956
    Prev
    Next
    INDEX
    Explanations

    shortest path distance or length

    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
    ëıħ
    -0.07
     Fres
    -0.07
    association
    -0.07
    çݯæ¯Ķ
    -0.06
     associations
    -0.06
    åĹ
    -0.06
    寡
    -0.06
    ãģ¡ãģ¯
    -0.06
    éģĵ
    -0.06
    Ahead
    -0.06
    POSITIVE LOGITS
     distances
    0.10
    è·Ŀ离
    0.10
    distance
    0.09
     distance
    0.09
    æľĢéķ¿
    0.09
     Distance
    0.09
    æľĢéķ¿çļĦ
    0.09
    è·ĿéĽ¢
    0.09
     longest
    0.08
    -terminal
    0.08
    Activations Density 0.004%

    No Known Activations