© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 554
    Prev
    Next
    INDEX
    Explanations

    "if" / "then" / "que"

    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
    Negative Logits
    è¿Ļæł·ä¸Ģç§į
    -0.07
    èĢĮ导èĩ´
    -0.07
    设为é¦ĸ页
    -0.07
    onner
    -0.07
    æł¼
    -0.06
    èĢĮæĹłæ³ķ
    -0.06
    atat
    -0.06
    [array
    -0.06
     λοι
    -0.06
     tact
    -0.06
    POSITIVE LOGITS
     it
    0.08
     hasilnya
    0.08
    å®ĥå°±æĺ¯
    0.08
    olia
    0.07
    å®ĥ
    0.07
    åħ³ç³»åĪ°
    0.07
    äºļäºİ
    0.07
    igure
    0.07
    å®ĥå°±
    0.07
    ila
    0.07
    Activations Density 0.024%

    No Known Activations