© 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. 14527
    Prev
    Next
    INDEX
    Explanations

    solid state, estimation, electron, gas, slab, tiled

    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
    è¿Ļ个
    -0.08
     supposedly
    -0.07
    воде
    -0.06
    боÑİ
    -0.06
    è¿Ļ个å°ı
    -0.06
    icles
    -0.06
    è¿Ļ个大
    -0.06
     somewhat
    -0.06
    ferences
    -0.06
    oved
    -0.06
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.08
    ä¹Ŀ天
    0.08
    æ³ķçŃī
    0.08
     berbasis
    0.07
     dedicated
    0.07
     Dedicated
    0.07
    ży
    0.07
    entai
    0.07
    -based
    0.07
    为çİĭ
    0.07
    Activations Density 0.069%

    No Known Activations