© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50375
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers

    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
    xBC
    -0.08
    åĴĮä½ľçĶ¨
    -0.08
    xBD
    -0.07
    ungan
    -0.07
    Uvs
    -0.07
    xDB
    -0.07
    inger
    -0.07
    Https
    -0.07
    ipl
    -0.07
    DataReader
    -0.07
    POSITIVE LOGITS
    ¿
    0.08
    »
    0.08
     dám
    0.07
    º
    0.07
    hest
    0.07
    Advertisements
    0.06
     corpus
    0.06
    ç½®ä¹ĭ
    0.06
    werpen
    0.06
    lated
    0.06
    Activations Density 0.085%

    No Known Activations