© 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. 26848
    Prev
    Next
    INDEX
    Explanations

    blog post

    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
    ä¹ĭäºİ
    -0.09
    åŃĺåľ¨äºİ
    -0.07
    åªĴä½ĵæĬ¥éģĵ
    -0.07
    alak
    -0.07
    cia
    -0.07
     dud
    -0.07
    ä¹ĭ为
    -0.07
    Ỿ
    -0.07
    謹
    -0.06
    åıĪä¸įæĺ¯
    -0.06
    POSITIVE LOGITS
    kke
    0.08
    Ïģγο
    0.08
    ä¸Ń使çĶ¨
    0.08
    -using
    0.07
    大æĦı
    0.07
    OnError
    0.07
    ä¸ŃæĮĩåĩº
    0.07
    ney
    0.07
    ä¸ŃæıIJåĪ°
    0.07
    详ç»Ĩ
    0.06
    Activations Density 0.184%

    No Known Activations