© 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. 27022
    Prev
    Next
    INDEX
    Explanations

    different reasons

    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
    ogar
    -0.09
    åĽºçĦ¶
    -0.09
    ä¹ĥèĩ³
    -0.08
    æľĢæł¹æľ¬
    -0.08
    ä¹Łä¸įåı¯èĥ½
    -0.07
    à¹ģมà¹īà¹ģà¸ķà¹Ī
    -0.07
     downright
    -0.07
    æĺ¯ä¸ĢåĪĩ
    -0.07
     celo
    -0.07
    纵çĦ¶
    -0.07
    POSITIVE LOGITS
    以ä¸Ģç§į
    0.09
    ä¸įåIJĮçļĦæĺ¯
    0.08
    西西
    0.08
    åħĭåĬĽ
    0.07
    éĺ³
    0.07
    rost
    0.07
    _QUAL
    0.07
     thereof
    0.07
    indy
    0.07
    åĴĮè´¨éĩı
    0.07
    Activations Density 0.308%

    No Known Activations