© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32921
    Prev
    Next
    INDEX
    Explanations

    commonly accepted

    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
    à¹Ģà¸Ľà¹ĩà¸Ļà¸ŀิà¹Ģศษ
    -0.09
    ä¸İä¼Ĺä¸įåIJĮçļĦ
    -0.08
    -native
    -0.08
    å¾Ī好å¥ĩ
    -0.08
    çī¹åĪ«å¥½
    -0.08
    åºĶæľīå°½æľī
    -0.08
    ä¸Ģæ°Ķ
    -0.08
    Ñħам
    -0.08
     znaj
    -0.08
    åı¯èĥ½åĩºçİ°
    -0.08
    POSITIVE LOGITS
    åħ¬è®¤
    0.15
     consensus
    0.15
    åħ¬è®¤çļĦ
    0.15
    åħ±è¯Ĩ
    0.14
    åħ±èŃĺ
    0.11
    主æµģ
    0.11
     accepted
    0.10
    ä¸Ģèĩ´è®¤ä¸º
    0.10
     mainstream
    0.09
    认为
    0.09
    Activations Density 0.164%

    No Known Activations