© 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. 2279
    Prev
    Next
    INDEX
    Explanations

    questions followed by certain words

    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
    erman
    -0.07
    kor
    -0.07
    errar
    -0.07
    bies
    -0.06
    çİ¥
    -0.06
    igs
    -0.06
    åı£è¯Ģ
    -0.06
    ÙĦاÙĦ
    -0.06
    åĩłæĿ¡
    -0.06
     Snowden
    -0.06
    POSITIVE LOGITS
    æĪĸ许æĺ¯
    0.09
    ;;;;
    0.08
    æĪĸèĢħæĺ¯
    0.08
    otch
    0.08
     Trang
    0.07
    亦æĪĸæĺ¯
    0.07
    pped
    0.07
    åıĪæĪĸèĢħ
    0.07
    LEAN
    0.07
    åIJİåıĪ
    0.07
    Activations Density 0.005%

    No Known Activations