© 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. 26178
    Prev
    Next
    INDEX
    Explanations

    proteins and molecules

    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
    è´Łåİĭ
    -0.08
    æ°Ķæµģ
    -0.08
    Ñħо
    -0.07
    åı¯ä»¥èĢĥèĻij
    -0.07
    ovit
    -0.07
    ucer
    -0.07
     меÑĤÑĢо
    -0.07
    outing
    -0.07
    æ´ŀåı£
    -0.07
    hofer
    -0.07
    POSITIVE LOGITS
     protein
    0.11
    èĽĭçĻ½è´¨
    0.10
     proteins
    0.10
    protein
    0.10
    ç»ĦæĪIJ
    0.09
    åĪĨåŃIJ
    0.09
     molecules
    0.09
    åĤ¨åŃĺ
    0.09
     molecular
    0.09
     molecule
    0.09
    Activations Density 0.041%

    No Known Activations