© 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. 48207
    Prev
    Next
    INDEX
    Explanations

    book content summaries

    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
    ikle
    -0.07
    æĢ»ä¸įèĥ½
    -0.07
    åĽºæľī
    -0.07
    æĸĩéĿĻ
    -0.07
    çī¹æ´¾
    -0.07
    æĪij们åŃ¦æł¡
    -0.07
    é»ĺ认çļĦ
    -0.07
    æľ¬æĬ¥è®°èĢħ
    -0.06
     aparentemente
    -0.06
    ween
    -0.06
    POSITIVE LOGITS
     comprehensive
    0.08
    uas
    0.08
    ook
    0.07
    å°±æĺ¯å¯¹
    0.07
     Coverage
    0.07
    åĮħæĭ¬äºĨ
    0.07
    è°ģä¼ļ
    0.07
    åħ¨éĿ¢çļĦ
    0.07
    åıĪä¸į失
    0.07
     coverage
    0.07
    Activations Density 0.208%

    No Known Activations