© 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. 43056
    Prev
    Next
    INDEX
    Explanations

    existing or already

    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
    lungen
    -0.08
    ä¸Ńåĩºçİ°
    -0.08
    ãģ°ãģĭãĤĬ
    -0.07
    ாமà¯į
    -0.07
    ivs
    -0.07
    lds
    -0.07
    lashes
    -0.07
    ungk
    -0.07
    å®Ĺ亲
    -0.07
    idl
    -0.07
    POSITIVE LOGITS
    à¸Ńยูà¹Īà¹ģลà¹īว
    0.20
     already
    0.19
    æľ¬æĿ¥å°±
    0.19
    already
    0.17
    æľ¬å°±
    0.14
     zaten
    0.14
    å·²ç»ıæĺ¯
    0.14
     Already
    0.14
    Already
    0.14
    就已ç»ı
    0.14
    Activations Density 0.112%

    No Known Activations