© 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. 34252
    Prev
    Next
    INDEX
    Explanations

    a or the before noun

    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
    åĮ£
    -0.07
    uks
    -0.07
    uern
    -0.06
     Baumwolle
    -0.06
    FormGroup
    -0.06
     Metropolitana
    -0.06
    endung
    -0.06
     aspects
    -0.06
    dol
    -0.06
    нан
    -0.06
    POSITIVE LOGITS
     áĭ¨
    0.09
    åĽĽå¹´çļĦ
    0.07
    åľŁåľ°è½¬è®©
    0.07
    ációs
    0.07
    æĹħ游度åģĩåĮº
    0.07
    åįģåĢį
    0.07
    æĺ¯éĩĩçĶ¨
    0.07
    è¿ĩéĩį
    0.07
    ames
    0.07
    -million
    0.06
    Activations Density 1.264%

    No Known Activations