© 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. 41448
    Prev
    Next
    INDEX
    Explanations

    protein export and trafficking

    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
     dug
    -0.07
    èıĩ
    -0.07
     hypnot
    -0.07
    éĻª
    -0.07
    踩
    -0.06
     covering
    -0.06
    æĻºèĢħ
    -0.06
     Pel
    -0.06
    opor
    -0.06
    åĭĺæİ¢
    -0.06
    POSITIVE LOGITS
     destined
    0.12
    缮çļĦåľ°
    0.09
    Export
    0.09
    export
    0.09
    -export
    0.09
     exported
    0.09
     Emb
    0.08
    è´¨éĩıæ£Ģæµĭ
    0.08
     PROCESS
    0.08
    urig
    0.08
    Activations Density 0.093%

    No Known Activations