© 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. 11914
    Prev
    Next
    INDEX
    Explanations

    a little better

    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
    agno
    -0.07
    åĴĮèī¯å¥½çļĦ
    -0.07
    å¾Īä½İ
    -0.07
    羯
    -0.07
    ä»»ä½ķä¸Ģç§į
    -0.06
    видко
    -0.06
    .flat
    -0.06
    平平å®ī
    -0.06
    ruÄį
    -0.06
    æľīåIJį
    -0.06
    POSITIVE LOGITS
     more
    0.23
    æĽ´åĬł
    0.22
    æĽ´ä¸º
    0.21
     clearer
    0.21
     lebih
    0.20
    æĽ´åħ·
    0.20
    å¾ĹæĽ´
    0.20
     richer
    0.20
     tighter
    0.20
    æĽ´å¤ļçļĦ
    0.20
    Activations Density 0.261%

    No Known Activations