© 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. 42957
    Prev
    Next
    INDEX
    Explanations

    protests against

    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
    -webpack
    -0.08
    åºĶéħ¬
    -0.08
     Porr
    -0.07
    åIJĿåķ¬
    -0.07
    çļĦå®īæİĴ
    -0.07
    å°Ĭ享
    -0.07
    getJSON
    -0.07
     divor
    -0.06
     Tropical
    -0.06
    çļĦç«ŀäºī
    -0.06
    POSITIVE LOGITS
    åıįæĬĹ
    0.11
     espont
    0.10
    äºīåıĸ
    0.10
    æĬĹè®®
    0.10
     protesting
    0.10
     spontaneously
    0.10
     spontan
    0.09
     spontaneous
    0.09
    éĽĨä¼ļ
    0.09
    èĩªåıij
    0.09
    Activations Density 0.302%

    No Known Activations