© 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. 13967
    Prev
    Next
    INDEX
    Explanations

    fire, weather, medical, history, construction

    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
    iris
    -0.06
    ált
    -0.06
    allest
    -0.06
    bili
    -0.06
    ¨
    -0.06
    å¼Ĥå½¢
    -0.06
    иÑĢа
    -0.06
    hés
    -0.06
    åŃ¦ä¹łåħ´è¶£
    -0.06
    ãĤ¹ãĥĪãĥ©
    -0.06
    POSITIVE LOGITS
    åĨį次
    0.24
    åĨį度
    0.21
    继ç»Ń
    0.20
    åĨįä¸Ģ次
    0.19
     continued
    0.19
     again
    0.18
    again
    0.18
    åĨįãģ³
    0.18
     erneut
    0.17
     повÑĤоÑĢно
    0.17
    Activations Density 0.556%

    No Known Activations