© 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. 2822
    Prev
    Next
    INDEX
    Explanations

    "but I"

    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
    æĪij们ä¸İ
    -0.07
    å¨Ĩ
    -0.07
    akon
    -0.07
    她ä¸İ
    -0.07
    (('
    -0.07
    Split
    -0.07
     Nghi
    -0.06
    à¸ŀัà¸ģ
    -0.06
    jang
    -0.06
    tait
    -0.06
    POSITIVE LOGITS
    两èĢħ
    0.18
    äºĮèĢħ
    0.17
    两èĢħçļĦ
    0.17
    åħ©èĢħ
    0.14
    åīįèĢħ
    0.12
    åIJİèĢħ
    0.12
     között
    0.11
     بÙĬÙĨÙĩÙħا
    0.11
    ä¹ĭéĹ´çļĦ
    0.11
     keduanya
    0.11
    Activations Density 0.088%

    No Known Activations