© 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. 49791
    Prev
    Next
    INDEX
    Explanations

    partition sizes

    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
    combe
    -0.07
    çĺŁ
    -0.07
    âĢ³
    -0.07
    ç¢
    -0.06
     terperinci
    -0.06
    è¿Ļæł·çļĦ
    -0.06
     //"
    -0.06
    çį
    -0.06
    害
    -0.06
    è¿Ļæł·ä¸Ģ个
    -0.06
    POSITIVE LOGITS
    ç¯ĩä¸Ģ
    0.09
    çī¹åĭĴ
    0.08
     {}:
    0.08
    åŁİ举
    0.07
    ีà¹Īย
    0.07
     âĶľâĶĢâĶĢ
    0.07
     primera
    0.07
    esses
    0.07
    èݱ德
    0.07
    eger
    0.07
    Activations Density 0.054%

    No Known Activations