© 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. 25866
    Prev
    Next
    INDEX
    Explanations

    mathematical equations with variables

    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
    å²±
    -0.08
    æ³ī
    -0.08
    repid
    -0.08
    æĬ¤çIJĨè´¹
    -0.08
    å°ĶèĴĻ
    -0.07
    emiz
    -0.07
    ä¸įèĭŁ
    -0.07
     Тад
    -0.07
    åħįè´¹åĴ¨è¯¢
    -0.07
    äºĶè°·
    -0.07
    POSITIVE LOGITS
     Scouts
    0.06
    ä½ĵä¼ļ
    0.06
     recip
    0.06
    åªĴä»ĭ
    0.06
     Prime
    0.06
    éĽį
    0.06
    akah
    0.06
    æİ¥åĬĽ
    0.06
    olog
    0.06
     prime
    0.06
    Activations Density 0.002%

    No Known Activations