© 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. 16553
    Prev
    Next
    INDEX
    Explanations

    numbers and money figures

    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
    former
    -0.07
    avar
    -0.07
    以èĩ´
    -0.07
    ikel
    -0.07
    ping
    -0.07
    lying
    -0.07
    åĪ°æł¡
    -0.07
    åIJĦ项è§Ħç«łåĪ¶åº¦
    -0.07
     former
    -0.06
    तिà¤ķ
    -0.06
    POSITIVE LOGITS
    kest
    0.07
    rave
    0.07
    orex
    0.07
     unmist
    0.07
    unen
    0.07
    ielt
    0.07
    raine
    0.07
    issance
    0.06
    ë¥
    0.06
    otle
    0.06
    Activations Density 0.007%

    No Known Activations