© 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. 18415
    Prev
    Next
    INDEX
    Explanations

    problems, story, boxes, questions

    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
    alom
    -0.09
    åıĬåħ¶
    -0.08
    mata
    -0.08
    ’s
    -0.08
    ÙĤداÙħ
    -0.08
    +","+
    -0.08
    +"'
    -0.07
    ubr
    -0.07
    paralleled
    -0.07
    ä¹ĭ为
    -0.07
    POSITIVE LOGITS
    ulla
    0.06
    åıĪä¸Ģ个
    0.06
    èģĶæĴŃ
    0.06
    æŶ
    0.06
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    0.06
    并åIJij
    0.06
    并æıIJä¾Ľ
    0.06
    Ñĩик
    0.06
    å¿«æĬ¥
    0.06
    è¿İæİ¥
    0.05
    Activations Density 0.737%

    No Known Activations