© 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. 9088
    Prev
    Next
    INDEX
    Explanations

    vacation club

    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
    票
    -0.08
    æ¡Ī
    -0.07
    表
    -0.07
    à¤Ńव
    -0.07
    bolt
    -0.07
    arto
    -0.07
    表åĴĮ
    -0.07
    à¹Īà¸Ńย
    -0.06
    åħļç»ĦæĪIJåijĺ
    -0.06
    vre
    -0.06
    POSITIVE LOGITS
    kj
    0.08
    ç½¢
    0.07
    almaz
    0.07
    rej
    0.07
    驾
    0.07
    kör
    0.06
     nub
    0.06
    Sampler
    0.06
    anst
    0.06
    arella
    0.06
    Activations Density 0.039%

    No Known Activations