© 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. 10742
    Prev
    Next
    INDEX
    Explanations

    `rip`, `ender`, `y`, `(x`, `head`, `pointers`, `Bluetooth`

    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
     itself
    -0.08
    ELY
    -0.07
    ardy
    -0.07
     bạc
    -0.07
    algo
    -0.06
     gri
    -0.06
    è¼
    -0.06
    -root
    -0.06
    bsp
    -0.06
     seg
    -0.06
    POSITIVE LOGITS
    (xs
    0.07
    å±ŀ
    0.07
    æĹģ
    0.07
    缸åħ³éĹ®çŃĶ
    0.07
    Pla
    0.07
    .visual
    0.06
    .rel
    0.06
    管好
    0.06
    ascus
    0.06
     Surge
    0.06
    Activations Density 0.027%

    No Known Activations