© 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. 8096
    Prev
    Next
    INDEX
    Explanations

    diffusion and transfer

    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
    #\
    -0.07
    åºŀ
    -0.07
    .office
    -0.07
    份
    -0.07
     bó
    -0.07
    êng
    -0.07
     spl
    -0.06
    ceph
    -0.06
    æĻ´
    -0.06
    itore
    -0.06
    POSITIVE LOGITS
    ä¸īåĮº
    0.08
    ayer
    0.08
     replen
    0.08
    大ä¸Ń
    0.08
    è¿Ļä¸ĢéĹ®é¢ĺ
    0.08
     سرعت
    0.08
    è·ijèħ¿
    0.07
    æµģéĢŁ
    0.07
    å¿«åĪ°
    0.07
    çķħéĢļ
    0.07
    Activations Density 0.007%

    No Known Activations