© 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. 15026
    Prev
    Next
    INDEX
    Explanations

    grocery input

    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
    èĩªå·±çļĦæĥ³æ³ķ
    -0.09
    arella
    -0.07
    çļĦæīĢæľīä½ľåĵģ
    -0.07
    ÑħÑĢо
    -0.07
    acher
    -0.07
    пÑı
    -0.07
    ÏĢη
    -0.07
    å¤ļå°ij人
    -0.07
    erra
    -0.07
    issant
    -0.07
    POSITIVE LOGITS
    æ´ŀ
    0.07
    ived
    0.07
    åħĪçĶŁè¯´
    0.06
    OfString
    0.06
    )').
    0.06
    åIJĮè¡Į
    0.06
    è¡Į
    0.06
    ihat
    0.06
     apar
    0.06
    ãĢıãĢİ
    0.06
    Activations Density 0.003%

    No Known Activations