© 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. 56774
    Prev
    Next
    INDEX
    Explanations

    simply, simpler, or simplification

    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
    $$$$
    -0.07
    åģĩæĹ¥
    -0.07
    æ¬
    -0.07
    à¸Ńม
    -0.07
    uttle
    -0.07
    åľ¨æīĢ
    -0.07
    egas
    -0.07
    ä¸Ģè¯ķ
    -0.07
    ĥģ
    -0.07
     sovere
    -0.06
    POSITIVE LOGITS
     simpler
    0.13
     simply
    0.11
    å¹²èĦĨ
    0.10
    ç®Ģåįķåľ°
    0.10
    缴æİ¥çĶ¨
    0.10
    ç®ĢåĮĸ
    0.09
     semplicemente
    0.09
     simpl
    0.09
    ç®Ģæ´ģ
    0.09
    å°±çĽ´æİ¥
    0.09
    Activations Density 0.024%

    No Known Activations