© 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. 49270
    Prev
    Next
    INDEX
    Explanations

    modified, designed, loving, dedicated, hidden

    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
    继ç»Ń使çĶ¨
    -0.08
    并使çĶ¨
    -0.08
    å¤ļä¸Ģ份
    -0.07
    å§ĭèĩ³
    -0.07
    atology
    -0.07
     naud
    -0.07
    åıĤèĢĥèµĦæĸĻ
    -0.07
    éľĢè¦ģ使çĶ¨
    -0.07
    æŁ¥çľĭæīĢæľī
    -0.07
    éģµä»İ
    -0.07
    POSITIVE LOGITS
    ç¼ĸæİĴ
    0.10
    ç²¾å¿ĥ
    0.10
     구ìĦ±ëIJľ
    0.09
    åĮĸå¤ĦçIJĨ
    0.09
    éħįç½®
    0.09
     ساختÙĩ
    0.08
    ç·¨
    0.08
    转åĮĸ
    0.08
    éħįçļĦ
    0.08
    éħįåĪ¶
    0.08
    Activations Density 0.516%

    No Known Activations