© 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. 17266
    Prev
    Next
    INDEX
    Explanations

    academic thesis

    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
    çŁ¥éģĵåIJĹ
    -0.08
    æĺŁæľŁå¤©
    -0.08
    åŁ¹è®Ńä¸Ńå¿ĥ
    -0.08
     вÑĤоÑĢник
    -0.07
    rieg
    -0.07
    å½ĵä¹ĭ
    -0.07
    èĢģå°ij
    -0.07
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.07
    åħļç»Ħ书记
    -0.07
    ç½IJ
    -0.07
    POSITIVE LOGITS
    çłĶ究çļĦ
    0.08
    论æĸĩ
    0.07
    NPC
    0.07
    åĴĮçłĶ究
    0.07
    çłĶ究æĪIJæŀľ
    0.07
    æĭŁ
    0.07
    çłĶç©¶å·¥ä½ľ
    0.07
    åѦä½į论æĸĩ
    0.07
     hips
    0.06
    çłĶ究æĸ¹æ³ķ
    0.06
    Activations Density 0.008%

    No Known Activations