© 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. 28920
    Prev
    Next
    INDEX
    Explanations

    religious sisters of charity

    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
     Kut
    -0.07
    çĨŁèĥ½
    -0.07
    nyi
    -0.06
    å©´
    -0.06
    ussen
    -0.06
    èĮħ
    -0.06
    posables
    -0.06
    åį³ä¾¿å¦ĤæѤ
    -0.06
    imary
    -0.06
    yron
    -0.06
    POSITIVE LOGITS
     unspecified
    0.09
    çļĦåħ¶ä»ĸ
    0.08
    åħ¨èĪ¬
    0.08
    à¸Ńืà¹Īà¸Ļà¹Ĩ
    0.08
    家å®Ŀ
    0.07
     ìłĦë°ĺ
    0.07
     lainnya
    0.07
    enge
    0.07
    éĥ½åĸľæ¬¢
    0.07
     such
    0.07
    Activations Density 0.921%

    No Known Activations