© 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. 32614
    Prev
    Next
    INDEX
    Explanations

    numbers (two, three, four)

    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
    åįģäºĶå¹´
    -0.08
    ä¹Ŀåįģ
    -0.08
    åĩłåįģå¹´
    -0.07
    äºĨä¸Ģ段æŶéĹ´
    -0.07
    äºĶçĻ¾
    -0.07
    äºĶåįģ
    -0.07
    ä¸ĥåįģ
    -0.07
    çĻ¾æĹ¥
    -0.07
    åħħ
    -0.07
     Fifty
    -0.07
    POSITIVE LOGITS
     two
    0.19
    two
    0.16
     deux
    0.16
     zwei
    0.16
     three
    0.16
    两个
    0.16
     TWO
    0.15
    åħ©åĢĭ
    0.15
     два
    0.14
     four
    0.14
    Activations Density 0.585%

    No Known Activations