© 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. 55045
    Prev
    Next
    INDEX
    Explanations

    code definition and 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
    æī¦
    -0.08
    emez
    -0.07
    _bases
    -0.07
    .charCodeAt
    -0.07
    coni
    -0.07
    çĴ
    -0.07
    äºĮåįģä¸ĥ
    -0.07
    arto
    -0.07
     Ký
    -0.07
    ilde
    -0.07
    POSITIVE LOGITS
    æľĢç»ĪçļĦ
    0.08
    Pid
    0.08
    è¾¾æĪIJçļĦ
    0.07
    nal
    0.06
    indsight
    0.06
    ifax
    0.06
    kking
    0.06
     Pid
    0.06
    kk
    0.06
    çĶŁæ´»ä¿Ŀéļľ
    0.06
    Activations Density 0.003%

    No Known Activations