© 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. 9219
    Prev
    Next
    INDEX
    Explanations

    unshaded cells connected

    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
    RowCount
    -0.07
    Å¡li
    -0.07
    çī¹éĩĮ
    -0.07
    æĹ¥çĶŁ
    -0.07
    缮æłĩä»»åĬ¡
    -0.07
     ÙħجÙħع
    -0.07
    ಣ
    -0.07
    ñana
    -0.07
    ä¸įå·®
    -0.06
    ssp
    -0.06
    POSITIVE LOGITS
     chosen
    0.09
    æīĢéĢī
    0.08
    çļĦä»»ä½ķ
    0.08
    æĶ¾çļĦ
    0.07
    chosen
    0.07
    æĶ¾éŀŃçĤ®
    0.07
    æĶ¾ç½®
    0.07
    ä¸¥æł¼è¦ģæ±Ĥ
    0.07
    éĢīæĭ©ä¸į
    0.07
    éĢīæĭ©çļĦ
    0.07
    Activations Density 0.008%

    No Known Activations