© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 725
    Prev
    Next
    INDEX
    Explanations

    json structure

    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
    Negative Logits
    ery
    -0.08
    adays
    -0.08
    .bz
    -0.08
    ä¸įéĶĻ
    -0.07
    onus
    -0.06
    oni
    -0.06
    ide
    -0.06
    è¶Ĭæĥ³
    -0.06
     passato
    -0.06
    δι
    -0.06
    POSITIVE LOGITS
    اÙĨØ´
    0.08
    åºĶå½ĵä¾Ŀçħ§
    0.08
    hofer
    0.08
    ANC
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    urred
    0.07
    fran
    0.07
    fes
    0.06
    åĬłæĭ¿å¤§
    0.06
    ANGED
    0.06
    Activations Density 0.059%

    No Known Activations