© 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. 37806
    Prev
    Next
    INDEX
    Explanations

    nodes with children or list elements

    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
    Reload
    -0.07
     Dak
    -0.07
    åħ¼èģĮ
    -0.06
    ziale
    -0.06
    ocode
    -0.06
    饶
    -0.06
     prior
    -0.06
     dav
    -0.06
     tracked
    -0.06
     commun
    -0.06
    POSITIVE LOGITS
     recur
    0.08
    mate
    0.07
    çļĦå°ıæīĭ
    0.07
    ä¸Ńå°ı
    0.07
    大åĪĢ
    0.07
    ILON
    0.07
    tof
    0.07
     Rec
    0.07
    mans
    0.07
    åĬŁ
    0.07
    Activations Density 0.053%

    No Known Activations