© 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. 2729
    Prev
    Next
    INDEX
    Explanations

    people met or encountered

    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
    çĶ·åĦ¿
    -0.08
    åĵįå½»
    -0.07
    åħ¨éĺŁ
    -0.07
    ersh
    -0.07
    kih
    -0.07
    ules
    -0.07
    ä¸ĵ家们
    -0.07
    .keyword
    -0.07
    åIJĦç»Ħ
    -0.07
    羡
    -0.07
    POSITIVE LOGITS
     whom
    0.15
    åĴĮèĩªå·±
    0.12
    ä¸İèĩªå·±
    0.12
    æ¯Ķèĩªå·±
    0.11
    è·Łèĩªå·±
    0.11
    缸å¤Ħ
    0.10
    å´ĩæĭľ
    0.09
    缸å¤ĦçļĦ
    0.09
     rencontré
    0.09
     ìĥģëĮĢë¡ľ
    0.09
    Activations Density 0.387%

    No Known Activations