© 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. 27216
    Prev
    Next
    INDEX
    Explanations

    question followed by "that"

    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
    /english
    -0.08
    æĪĸåħ¶å®ĥ
    -0.07
    igne
    -0.07
    åĴĮçĻ½
    -0.07
     Christi
    -0.07
    emsp
    -0.07
    ä¸įèĥ½ä½¿çĶ¨
    -0.07
    áŀĶáŁĭ
    -0.07
    дÑĢоб
    -0.07
    åĴĮä¸ī
    -0.06
    POSITIVE LOGITS
    æ¯Ķå¦Ĥ说
    0.09
    olo
    0.08
    æ¯Ķå¦Ĥ
    0.08
    æ¯Ķå¦Ĥåľ¨
    0.08
    æį¢åı¥è¯Ŀ说
    0.08
    VIC
    0.07
    cha
    0.07
    æľĪçĶŁ
    0.07
    ENO
    0.07
    ä¸ĩä¸Ģ
    0.07
    Activations Density 0.935%

    No Known Activations