© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49725
    Prev
    Next
    INDEX
    Explanations

    using or based on

    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
    稿件æĿ¥æºIJ
    -0.09
    odat
    -0.08
    çĶ±æĶ¿åºľ
    -0.08
     кÑĢип
    -0.08
    æł¹æį®åħ¶
    -0.07
    »
    -0.07
    alisi
    -0.07
    EPROM
    -0.07
    åħ³äºİæĪij们
    -0.07
    aise
    -0.07
    POSITIVE LOGITS
     concepts
    0.07
    以ä¸ĭæĸ¹å¼ı
    0.07
    abaj
    0.07
    heen
    0.07
    ä»Ģä¹Īåij¢
    0.07
     própria
    0.07
    hof
    0.07
    ÏĦαι
    0.07
    gäng
    0.06
     "
    0.06
    Activations Density 0.027%

    No Known Activations