© 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. 17070
    Prev
    Next
    INDEX
    Explanations

    accretion, disruption event, X-ray

    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
    ÙĩÙĨ
    -0.07
    å¼Ģç«ĭ
    -0.07
    çĪĨ竹
    -0.06
    ucks
    -0.06
    ocus
    -0.06
     airing
    -0.06
     coz
    -0.06
    èµ°åĩºäºĨ
    -0.06
    åŁİ乡建设
    -0.06
    å¾·éŁ³
    -0.06
    POSITIVE LOGITS
    -fed
    0.09
     funnel
    0.09
    潤
    0.09
     feeding
    0.09
    lub
    0.08
    tev
    0.08
    feeding
    0.08
    润æ»ij
    0.08
     поÑģÑĤÑĥплениÑı
    0.08
     onto
    0.08
    Activations Density 0.006%

    No Known Activations