© 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. 23450
    Prev
    Next
    INDEX
    Explanations

    Founding Fathers

    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
    æ§ĥ
    -0.08
    εί
    -0.08
    cati
    -0.08
    åĪijèѦ
    -0.08
     Pyongyang
    -0.08
    éĶĪéĴ¢
    -0.08
     Bashar
    -0.08
    agne
    -0.07
    Schedulers
    -0.07
    arbe
    -0.07
    POSITIVE LOGITS
     constitutional
    0.09
     settlers
    0.08
     Constitutional
    0.08
     militia
    0.08
     federal
    0.08
     bic
    0.08
    constitutional
    0.07
     bounty
    0.07
    æ°ijåħµ
    0.07
     writ
    0.07
    Activations Density 0.178%

    No Known Activations