© 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. 10131
    Prev
    Next
    INDEX
    Explanations

    advocate, hardware, site, anniversary

    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
    ãĥ¬ãĤ¹
    -0.07
    æľĢ常è§ģçļĦ
    -0.06
    izi
    -0.06
    è¯Ŀ说
    -0.06
     bÃŃ
    -0.06
    bÃŃ
    -0.06
    èī¯
    -0.06
    çļĦçİ°å®ŀ
    -0.06
     beh
    -0.06
    åĽłä¸ºæ²¡æľī
    -0.06
    POSITIVE LOGITS
    çŃīçī¹æ®Ĭ
    0.09
    æľīçī¹æ®Ĭ
    0.08
    çī¹æ®ĬæĢ§
    0.08
    epen
    0.08
    agus
    0.08
    åIJĮæŃ¥
    0.08
    çī¹æ®ĬçļĦ
    0.08
    -related
    0.08
    èĩªæĭĶ
    0.08
     tersendiri
    0.07
    Activations Density 0.114%

    No Known Activations