© 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. 18646
    Prev
    Next
    INDEX
    Explanations

    expecting at

    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
    åľ¨åģļ
    -0.08
    è¿Ľä¸ĢæŃ¥è§ĦèĮĥ
    -0.08
    æĪĸåĽł
    -0.07
     ÙĨÙĤ
    -0.07
    åľ¨ä¸º
    -0.06
    踩çĿĢ
    -0.06
    ä¾®
    -0.06
    åľ¨çĶ¨
    -0.06
    为满足
    -0.06
     Suns
    -0.06
    POSITIVE LOGITS
    AndWait
    0.13
     expecting
    0.12
    æĶ¾ä»»
    0.11
    让åħ¶
    0.11
     hoping
    0.10
    à¸Ľà¸¥à¹Īà¸Ńยà¹ĥหà¹ī
    0.10
    让å®ĥ
    0.10
    æĺ¯è®©
    0.09
    .expect
    0.09
    让å®ĥ们
    0.09
    Activations Density 0.395%

    No Known Activations