© 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. 11202
    Prev
    Next
    INDEX
    Explanations

    nucleons, venticle, abstract class, Component

    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
    Sys
    -0.08
     Sys
    -0.08
    SYS
    -0.07
    á»ĩt
    -0.07
     Wall
    -0.07
    bod
    -0.06
    Ñīи
    -0.06
    ded
    -0.06
    rog
    -0.06
    oug
    -0.06
    POSITIVE LOGITS
    çīĩçīĩ
    0.08
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.08
    ttö
    0.07
    º¼
    0.07
    çĶ±åŃ¦æł¡
    0.07
     kaž
    0.07
    ãģ©ãģ¡ãĤī
    0.07
    èĤĩ
    0.07
    nameof
    0.07
    kdir
    0.07
    Activations Density 0.093%

    No Known Activations