© 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. 44947
    Prev
    Next
    INDEX
    Explanations

    simple explanations

    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
    æľªå¤®
    -0.06
    çļĦæľīåħ³è§Ħå®ļ
    -0.06
    elo
    -0.06
    <Array
    -0.06
    Array
    -0.06
    éĤ£äºĽäºº
    -0.06
    满头
    -0.06
     Wach
    -0.06
    éĵºå¤©çĽĸ
    -0.06
    errmsg
    -0.06
    POSITIVE LOGITS
    以ä¸Ĭ
    0.11
    å°±æĺ¯è¿Ļæł·
    0.11
    ä¸Ĭè¿°
    0.11
    å°±æĺ¯è¿Ļä¹Ī
    0.10
    以ä¸Ĭæĺ¯
    0.09
    éĢļè¿ĩ以ä¸Ĭ
    0.09
    çļĦè¿ĻäºĽ
    0.09
    以ä¸Ĭå°±æĺ¯
    0.09
    ples
    0.09
    çľĭä¼¼
    0.09
    Activations Density 0.376%

    No Known Activations