© 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. 23618
    Prev
    Next
    INDEX
    Explanations

    anchor tags with href attributes

    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
    eens
    -0.07
    alk
    -0.07
    à¦ķà§įষ
    -0.07
    aner
    -0.07
    ubble
    -0.07
    utki
    -0.07
    hiri
    -0.07
     Expo
    -0.07
    orama
    -0.07
    åIJĪæł¼åIJİ
    -0.07
    POSITIVE LOGITS
    [href
    0.08
    rels
    0.08
    IX
    0.08
    lesh
    0.08
    ogu
    0.07
    (href
    0.07
     href
    0.07
    lesa
    0.07
    ¦
    0.07
    mailto
    0.07
    Activations Density 0.022%

    No Known Activations