© 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. 61887
    Prev
    Next
    INDEX
    Explanations

    hex data prefixes

    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
    ä¸ĬåĽ¾
    -0.07
    xDD
    -0.07
    ville
    -0.06
    夹
    -0.06
    ìĬµ
    -0.06
    çłĶ究åŀĭ
    -0.06
     nar
    -0.06
    头åı·
    -0.06
    zk
    -0.06
     confer
    -0.06
    POSITIVE LOGITS
    enam
    0.09
    siz
    0.07
    entar
    0.07
    ynes
    0.07
    ×ijר×Ļ
    0.07
     overe
    0.07
    embers
    0.07
    é«ĺæ¡¥
    0.07
    ystore
    0.07
    åħ´
    0.07
    Activations Density 0.023%

    No Known Activations