© 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. 61646
    Prev
    Next
    INDEX
    Explanations

    algebraic structures

    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
    innan
    -0.08
    æĦĪæ¼ĶæĦĪ
    -0.08
    å°±ç®ĹäºĨ
    -0.08
    .Companion
    -0.08
    бак
    -0.07
    è¿ĺçĶ¨
    -0.07
    è¶Ĭæĥ³
    -0.07
     Hierzu
    -0.07
    ä¸Ģ缴éĥ½åľ¨
    -0.07
    Õ¼
    -0.07
    POSITIVE LOGITS
    å¿ħå®ļ
    0.09
    ä¸Ģå®ļæĺ¯
    0.08
    è¿Ļæĺ¯åĽłä¸º
    0.07
    å¿ħãģļ
    0.07
    çĵ¦
    0.07
    å¿ħ
    0.07
     Due
    0.07
    ä¸ĢèĪ¬ä¸º
    0.07
    èĢĮä¸Ķ
    0.07
     moreover
    0.07
    Activations Density 0.012%

    No Known Activations