© 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. 51581
    Prev
    Next
    INDEX
    Explanations

    machines produce

    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
     اÛĮÙĨÚ©Ùĩ
    -0.07
    ayang
    -0.07
    ehr
    -0.07
    æľ¬è´¨
    -0.06
    æľīä¸Ģ款
    -0.06
    allinen
    -0.06
    istou
    -0.06
    å¸Ĥä¸Ń
    -0.06
    äºĨè§£æĽ´å¤ļ
    -0.06
     olyan
    -0.06
    POSITIVE LOGITS
    สรà¹īาà¸ĩà¸Ĥึà¹īà¸Ļ
    0.09
     entails
    0.09
     betreft
    0.09
     might
    0.08
    éĥ¨åĪĨç»ĦæĪIJ
    0.08
     entail
    0.08
    çľĭçľĭåIJ§
    0.08
    à¹ĥà¸Ĭà¹īà¹Ħà¸Ķà¹ī
    0.08
     heck
    0.08
    å½ĵä¹ĭæĹłæĦ§
    0.08
    Activations Density 0.376%

    No Known Activations