© 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. 45428
    Prev
    Next
    INDEX
    Explanations

    aripiprazole, Primetime, Sarbanes Oxley

    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
    æĪIJèį¯
    -0.07
    çī©çļĦ
    -0.07
     Nack
    -0.07
    åįĪ
    -0.07
    SWG
    -0.07
    ä¸įåħį
    -0.06
     compareTo
    -0.06
    HLT
    -0.06
    GBK
    -0.06
    ãĥ¬ãĥĥ
    -0.06
    POSITIVE LOGITS
    诸å¦Ĥ
    0.09
    prite
    0.08
    ork
    0.08
    ORK
    0.07
    ragon
    0.07
    çĨŁæĤī
    0.07
    heed
    0.07
    acz
    0.07
    éĢĤçĶ¨
    0.07
    è¾Ī
    0.07
    Activations Density 1.582%

    No Known Activations