© 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. 12734
    Prev
    Next
    INDEX
    Explanations

    option letters

    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
    gles
    -0.07
    "s
    -0.07
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.07
    ä¸ĭåIJĮ
    -0.07
    .jet
    -0.07
    æľ¬ç§ijæ¯ķä¸ļçĶŁ
    -0.06
    æľīäºĮ
    -0.06
    .INT
    -0.06
    ä¹ĭå¹´
    -0.06
    æ±ŁåŁİ
    -0.06
    POSITIVE LOGITS
    æĪijä¹Łåİ»
    0.08
    æĪij们æĿ¥
    0.07
    åįķéĢīé¢ĺ
    0.07
    bers
    0.07
    apest
    0.06
    åĵİ
    0.06
    æĶ¿æ²»å»ºè®¾
    0.06
     erster
    0.06
    éļı便
    0.06
    ä¾ł
    0.06
    Activations Density 0.008%

    No Known Activations