© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2821
    Prev
    Next
    INDEX
    Explanations

    "Presidente"

    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
     anyways
    -0.09
    èIJĥ
    -0.08
    æĤĦæĤĦçļĦ
    -0.08
    anker
    -0.08
     QLD
    -0.08
    太å®Ī
    -0.07
    klen
    -0.07
    Idx
    -0.07
    宣åijĬ
    -0.07
    ltk
    -0.07
    POSITIVE LOGITS
     Budget
    0.09
    é¢Ħç®Ĺ
    0.09
     subparagraph
    0.08
     pursuant
    0.08
     budget
    0.08
     notwithstanding
    0.07
     pending
    0.07
     бÑİджеÑĤ
    0.07
    virt
    0.07
    Budget
    0.07
    Activations Density 0.388%

    No Known Activations