© 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. 40335
    Prev
    Next
    INDEX
    Explanations

    first time ever

    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
    .reject
    -0.08
    eres
    -0.08
    念念ä¸įå¿ĺ
    -0.07
    å·²æĪIJ
    -0.07
    ewan
    -0.07
    anz
    -0.07
    sthrough
    -0.07
    ếu
    -0.07
    å°ı家
    -0.07
     relentlessly
    -0.07
    POSITIVE LOGITS
    åīįæīĢæľªæľīçļĦ
    0.17
     впеÑĢвÑĭе
    0.15
    åīįæīĢæľª
    0.14
    第ä¸Ģ次
    0.13
    é¦ĸ次
    0.12
    ä»İæĿ¥æ²¡æľī
    0.12
     unprecedented
    0.12
     erstmals
    0.12
    é¦ĸæ¬¡åľ¨
    0.12
    -ever
    0.12
    Activations Density 0.514%

    No Known Activations